WO2024027210A1 - 用于机器人的控制方法、装置、电子设备及存储介质 - Google Patents

用于机器人的控制方法、装置、电子设备及存储介质 Download PDF

Info

Publication number
WO2024027210A1
WO2024027210A1 PCT/CN2023/089464 CN2023089464W WO2024027210A1 WO 2024027210 A1 WO2024027210 A1 WO 2024027210A1 CN 2023089464 W CN2023089464 W CN 2023089464W WO 2024027210 A1 WO2024027210 A1 WO 2024027210A1
Authority
WO
WIPO (PCT)
Prior art keywords
target
point
robot
vector
laser
Prior art date
Application number
PCT/CN2023/089464
Other languages
English (en)
French (fr)
Inventor
陈若龙
Original Assignee
北京京东乾石科技有限公司
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by 北京京东乾石科技有限公司 filed Critical 北京京东乾石科技有限公司
Publication of WO2024027210A1 publication Critical patent/WO2024027210A1/zh

Links

Classifications

    • G—PHYSICS
    • G05—CONTROLLING; REGULATING
    • G05D—SYSTEMS FOR CONTROLLING OR REGULATING NON-ELECTRIC VARIABLES
    • G05D1/00—Control of position, course, altitude or attitude of land, water, air or space vehicles, e.g. using automatic pilots
    • G05D1/02—Control of position or course in two dimensions
    • G05D1/021—Control of position or course in two dimensions specially adapted to land vehicles
    • G05D1/0212—Control of position or course in two dimensions specially adapted to land vehicles with means for defining a desired trajectory

Definitions

  • the present disclosure relates to the technical field of intelligent robots, and more specifically, to a control method, device, electronic equipment, media and program products for robots.
  • robots are increasingly used in many fields such as industrial and agricultural production, construction, logistics and daily life.
  • robots usually enter and exit the elevator.
  • the robot is usually required to find a parking spot based on the space inside the elevator to successfully complete the task of entering the elevator.
  • the method for a robot to enter an elevator is generally to reduce the envelope composed of laser points struck inside the elevator to a certain proportion to obtain the movable space of the robot, and then control the robot to enter the elevator.
  • the inventor found that there are at least the following problems in related technologies: when the envelope formed by the laser point is irregular, the accuracy of the robot's movable space obtained by using the above method is low, thereby affecting the robot's entry Elevator smoothness and success rate.
  • the present disclosure provides a control method, device, electronic device, medium and program product for a robot.
  • One aspect of the present disclosure provides a control method for a robot, including:
  • the movable space is determined based on the laser data collected by the above-mentioned robot, wherein the above-mentioned movable space is formed by n movable space points, where n ⁇ 1;
  • n movable space points For each of the above-mentioned n movable space points, determine the space vector used to characterize the spatial relationship between the target point and the above-mentioned movable space point, and obtain n above-mentioned space vectors, wherein the above-mentioned target point is located on the aforementioned robot;
  • the movement state of the above-mentioned robot is controlled according to n above-mentioned space vectors.
  • the above-mentioned control of the movement state of the above-mentioned robot according to n above-mentioned space vectors includes:
  • the target vectors that intersect with the equivalent coordinate vectors of the above-mentioned ladder doors are screened from the n above-mentioned space vectors to obtain a target vector set, wherein the above-mentioned equivalent coordinate vectors are used to characterize the above-mentioned ladder doors.
  • the above designated point is located outside the above-mentioned target elevator and is close to the door groove of the above-mentioned target elevator;
  • the above-mentioned robot is controlled to enter the above-mentioned target elevator through the above-mentioned elevator door, wherein the above-mentioned target is movable
  • the spatial points correspond to the above target vectors.
  • the above-mentioned laser data includes angle data of the laser point
  • the above-mentioned determination of the movable space based on the laser data collected by the above-mentioned robot includes:
  • the laser points that meet the preset angle threshold are determined to obtain the target laser point set, wherein the above-mentioned preset angle threshold includes a movable space determined according to the laser points within the above-mentioned preset angle threshold, which can cover The elevator area of the above-mentioned target elevator;
  • the above-mentioned movable space is determined based on the above-mentioned target laser data.
  • the above target laser point set includes k target laser points, where k ⁇ 1;
  • the above-mentioned determination of the above-mentioned movable space based on the above-mentioned target laser data includes:
  • the above-mentioned movable space is determined according to the k boundary values of the above-mentioned movable space points.
  • the above-mentioned determination of the movable spatial point boundary value in the above-mentioned laser direction includes:
  • Operation S2 for the i-th target laser point in the above-mentioned target laser point set, when the above-mentioned i-th target laser point is rotated by the above-mentioned target angle, determine the i-th lateral distance corresponding to the above-mentioned i-th target laser point, where 1 ⁇ i ⁇ k;
  • Operation S3 when the i-th lateral distance is less than a preset lateral distance threshold, obtain the ordinate value of the i-th target laser point, wherein the preset lateral distance threshold represents the lateral obstacle reference range of the robot;
  • Operation S4 when the ordinate value of the i-th target laser point is less than the current feasible boundary threshold, use the ordinate value of the i-th target laser point to update the current feasible boundary threshold to obtain an updated feasible boundary threshold;
  • Operation S5 Traverse the above-mentioned target laser point set, and perform operations S2-S4 cyclically to cyclically update the current feasible boundary threshold. After traversing the target laser points in the above-mentioned target laser point set, the update of the current feasible boundary threshold is completed, and the final feasible boundary threshold is obtained. boundary threshold;
  • the above-mentioned final feasible boundary threshold is determined to be the movable spatial point boundary value in the above-mentioned laser direction.
  • the above control method for a robot further includes:
  • the above control method for a robot further includes:
  • the forward target point Before controlling the robot to enter the target elevator through the elevator door, determine the forward target point from the target movable space points according to the target vector set, wherein the direction of the forward target point is the advancement of the robot. direction.
  • the above-mentioned target vector set includes m above-mentioned target vectors, m ⁇ 1;
  • the above-mentioned determination of the forward target point from the above-mentioned target movable space point according to the above-mentioned target vector set includes:
  • the above reference vector is A vector representing the spatial relationship between the above-mentioned target point and the central equivalent point of the above-mentioned target elevator;
  • the forward target point is determined from the target movable space points.
  • determining the forward target point from the target movable space point based on the m absolute values of the included angles includes:
  • the above-mentioned target vector set includes m above-mentioned target vectors, m ⁇ 1;
  • the above-mentioned determination of the forward target point from the above-mentioned target movable space point according to the above-mentioned target vector set includes:
  • the reference value is determined based on the distance from the above-mentioned target extension point to the above-mentioned equivalent coordinate vector, the vector angle value corresponding to the above-mentioned target vector and the rotation radius of the above-mentioned robot;
  • the above control method for a robot further includes:
  • the above-mentioned robot is controlled to move in the direction of the above-mentioned forward target point, wherein the above-mentioned preset value is based on the speed of the above-mentioned robot, the speed of the above-mentioned robot
  • the acceleration and distance compensation values are determined.
  • control device for a robot including:
  • the first control module is used to control the robot to move to the target waiting position corresponding to the target elevator;
  • the first determination module is used to determine the movable space based on the laser data collected by the robot when it is determined that the elevator door of the target elevator is open, wherein the movable space is formed by n movable space points, Among them, n ⁇ 1;
  • the second determination module is used to determine, for each of the above-mentioned n movable space points, a space vector used to characterize the spatial relationship between the target point and the above-mentioned movable space point, and obtain n above-mentioned space vectors. , where the above target point is located on the above robot; and
  • the second control module is used to control the movement state of the above-mentioned robot according to the n above-mentioned space vectors.
  • Another aspect of the present disclosure provides an electronic device, including: one or more processors; a memory for storing one or more programs, wherein when the one or more programs are processed by the one or more processors When executed, one or more processors are caused to execute the above control method for the robot.
  • Another aspect of the disclosure provides a computer-readable storage medium storing computer-executable instructions that, when executed, are used to implement the methods described in embodiments of the disclosure.
  • Another aspect of the disclosure provides a computer program including computer-executable instructions that, when executed, are used to implement the methods described in embodiments of the disclosure.
  • the robot is controlled to move to the target waiting position corresponding to the target elevator, and then when the elevator door of the target elevator is opened, the movable space is determined based on the laser data collected by the robot, and then the movable space is determined.
  • the space vector used to characterize the spatial relationship between the target point and the movable space point obtain n space vectors, and then control the moving state of the robot based on the n space vectors. Therefore, the technical problem of poor scaling effect when the envelope is irregular, which affects the performance of the robot entering the elevator, is at least partially overcome, thereby achieving the technical effect of improving the smoothness and success rate of the robot entering the elevator.
  • FIG. 1 schematically illustrates an exemplary system architecture to which control methods and devices for robots may be applied according to embodiments of the present disclosure
  • Figure 2 schematically shows a flow chart of a control method for a robot according to an embodiment of the present disclosure
  • Figure 3 schematically illustrates a schematic diagram of a target elevator area according to an embodiment of the present disclosure
  • Figure 4 schematically shows a flow chart of a control method for a robot according to another embodiment of the present disclosure
  • Figure 5 schematically shows a flow chart of a movable space determination method according to an embodiment of the present disclosure
  • Figure 6 schematically shows a flow chart of a movable space point boundary value determination method according to an embodiment of the present disclosure
  • Figure 7 schematically shows a schematic diagram of an elevator area including a target extension point according to an embodiment of the present disclosure
  • Figure 8 schematically shows a flow chart of a method for determining whether a robot has completely entered an elevator according to an embodiment of the present disclosure
  • Figure 9 schematically shows a flow chart of a method for determining an alternative forward target point according to an embodiment of the present disclosure
  • Figure 10 schematically shows a structural block diagram of a control device for a robot according to an embodiment of the present disclosure.
  • Figure 11 schematically shows a block diagram of an electronic device suitable for implementing the above-described method according to an embodiment of the present disclosure.
  • the technology of robot entering the elevator usually places the robot inside the elevator.
  • the envelope composed of laser points is reduced by a certain proportion to obtain the movable space of the robot, and then a target point that can satisfy the robot's entry is found in the movable space to control the robot to enter the elevator.
  • the inventor found that there are at least the following problems in the related technology: the above-mentioned method of reducing the envelope composed of the laser spots hit by the robot inside the elevator to obtain the movable space of the robot, in the envelope
  • the scaling effect is poor when it is irregular, which will affect the performance of the robot entering the elevator.
  • the present disclosure provides a control method for a robot to address the above technical problems, including: controlling the robot to move to a target waiting position corresponding to the target elevator; when it is determined that the elevator door of the target elevator is open, The movable space is determined according to the laser data collected by the above-mentioned robot, wherein the above-mentioned movable space is enclosed by n movable space points, where n ⁇ 1; for each movable space among the above-mentioned n movable space points space point, determine the space vector used to characterize the spatial relationship between the target point and the above-mentioned movable space point, obtain n above-mentioned space vectors, wherein the above-mentioned target point is located on the above-mentioned robot; and control the above-mentioned robot according to the n above-mentioned space vectors mobile status.
  • the robot is controlled to move to the target waiting position corresponding to the target elevator, and then when the elevator door of the target elevator is opened, the movable space is determined based on the laser data collected by the robot, and then the movable space is determined.
  • the space vector used to characterize the spatial relationship between the target point and the movable space point obtain n space vectors, and then control the moving state of the robot based on the n space vectors. Therefore, the technical problem of poor scaling effect when the envelope is irregular, which affects the performance of the robot entering the elevator, is at least partially overcome, thereby achieving the technical effect of improving the smoothness and success rate of the robot entering the elevator.
  • FIG. 1 schematically illustrates an exemplary system architecture 100 to which control methods and devices for robots may be applied according to embodiments of the present disclosure.
  • Figure 1 is only an example of a system architecture to which embodiments of the present disclosure can be applied, to help those skilled in the art understand the technical content of the present disclosure, but does not mean that the embodiments of the present disclosure cannot be used in other applications.
  • the system architecture 100 may include a robot 101, Elevators 102, 103, network 104 and control center 105.
  • the network 104 is used as a medium for providing a communication link between the robot 101 and the control center 105 .
  • Network 104 may include various connection types, such as wired and/or wireless communication links, and the like.
  • the operator can use the control center 105 to send operating instructions to the robot 101 through the network 104, so that the robot 101 moves to the waiting position of any one of the elevators 102 and 103 (for example, the elevator 102), or the robot 101 moves according to the driving task.
  • the robot 101 determines the movable space in the elevator 102 based on the collected laser data, and determines whether the movable space in the elevator 102 meets the entry conditions.
  • the robot 101 will continue to perform the elevator entry task only when the entry conditions are met. If the movable space does not meet the entry conditions, the robot 101 will not enter the elevator and will end the elevator entry task.
  • the control center 105 may be a control center that provides various control instructions, for example, sending inspection instructions to the robot 101, sending movement position instructions to the robot 101, etc.
  • control method for a robot provided by the embodiment of the present disclosure can generally be executed by the robot 101 .
  • the control device for the robot provided by the embodiment of the present disclosure may generally be provided in the robot 101 .
  • the control method for a robot provided by the embodiment of the present disclosure can also be executed by a server or server cluster that is different from the robot 101 and capable of communicating with the robot 101 .
  • the control device for a robot provided by the embodiment of the present disclosure may also be provided in a server or server cluster that is different from the robot 101 and capable of communicating with the robot 101 .
  • the robot 101 transmits the collected laser data to the server cluster, and then the server cluster analyzes the laser data, determines the movable space, and determines whether the movable space meets the conditions for entering the elevator, and then sends the analysis results to the robot 101 for convenience Control the movement state of the robot 101.
  • FIG. 2 schematically shows a flowchart of a control method for a robot according to an embodiment of the present disclosure.
  • the control method for a robot of this embodiment includes operations S210 to S240.
  • the robot is controlled to move to a target waiting position corresponding to the target elevator.
  • a robot when a robot enters a new operation scene, it needs to scan the global map of the scene or obtain the global map of the scene, and then perform corresponding tasks according to the robot's position in the global map to perform automatic operations.
  • the global map may include the locations of various areas, such as room locations, elevator locations, entrance and exit locations, etc.
  • the elevator can use polygons to represent the outline of the elevator to identify the location of the elevator door.
  • the robot can determine the elevator position and waiting place based on the global map, and then move to the target waiting position directly in front of the elevator door and a certain distance away from the elevator door according to the set instructions.
  • the movable space is determined based on the laser data collected by the robot, wherein the movable space is formed by n movable space points, where n ⁇ 1.
  • the robot after the robot reaches the target waiting position, it needs to determine whether the elevator door of the target elevator is open. If the elevator door of the target elevator is open, the movable space is determined based on the laser data collected by the robot.
  • the laser data collected by the robot may be preprocessed data such as filtering and sparsification, and the preprocessed data is converted into data in the robot coordinate system.
  • a space vector used to characterize the spatial relationship between the target point and the movable space point is determined, and n space vectors are obtained, where, The above target point is located on the above robot.
  • the target point may be the center point of the robot.
  • the space vector can be a vector with the target point and the movable space point as endpoints.
  • the moving state of the robot may include maintaining the target waiting position without entering the target elevator, and may also include entering the target elevator through the elevator door of the target elevator.
  • the robot is controlled to move to the target waiting position corresponding to the target elevator, and then when the elevator door of the target elevator is opened, the movable space is determined based on the laser data collected by the robot, and then the movable space is determined.
  • the space vector used to characterize the spatial relationship between the target point and the movable space point obtain n space vectors, and then control the moving state of the robot based on the n space vectors. Therefore, the technical problem of poor scaling effect when the envelope is irregular, which affects the performance of the robot entering the elevator, is at least partially overcome, thereby achieving the technical effect of improving the smoothness and success rate of the robot entering the elevator.
  • the above method further includes: the robot determines the current movable space according to the collected laser data, and uses the vector cross product method to determine the vector composed of the spatial point of the current movable space and the center point of the robot, and the vector with the elevator door Whether there is an intersection point between the inner vectors. If there is an intersection point, it means the elevator door is open.
  • the above method further includes: the robot counts the number of laser rays greater than a preset value based on the distance between itself and the elevator door to determine whether the elevator door is open.
  • the above-mentioned control of the movement state of the above-mentioned robot according to the n above-mentioned space vectors includes: filtering the equivalent coordinate vector of the above-mentioned elevator door from the n above-mentioned space vectors. Intersect the target vectors to obtain a target vector set, in which the above-mentioned equivalent coordinate vector is used to represent the coordinate vector of the spatial relationship between equivalent points on the above-mentioned elevator door.
  • the above-mentioned designated point is located outside the above-mentioned target elevator and is close to the above-mentioned target elevator.
  • the elevator door groove when the distance from the intersection point between the above-mentioned target vector and the above-mentioned equivalent coordinate vector to the target movable space point meets the preset distance condition, control the above-mentioned robot to enter the above-mentioned target elevator through the above-mentioned elevator door, Wherein, the above-mentioned target movable space point corresponds to the above-mentioned target vector.
  • the preset distance may be f ⁇ R, where f is a coefficient, R is the rotation radius of the robot, and generally f should be greater than 1.
  • the elevator entry task is only performed when the elevator entry conditions are met to avoid the robot getting stuck in the elevator door. Groove location.
  • the above method further includes: ending the ladder entry task when the distance from the intersection point between the above target vector and the above equivalent coordinate vector to the target movable space point does not meet the preset distance condition.
  • the coordinates of the four vertices of the rectangle are used to identify the target elevator.
  • the robot can obtain the four vertex coordinates of the target elevator from the global map.
  • Figure 3 schematically illustrates a schematic diagram of a target elevator area according to an embodiment of the present disclosure.
  • the four vertices of the target elevator are G1, G2, G3 and G4 respectively.
  • the area composed of G1, G2, G3 and G4 is the inner area of the target elevator.
  • Point P1 is the movable space point inside the elevator.
  • point P2 is the movable space point outside the elevator.
  • the area composed of points G1, G4, A and B is the elevator door groove area, the center point of the robot is point O, and the target waiting position is point E.
  • FIG. 4 schematically shows a flowchart of a control method for a robot according to another embodiment of the present disclosure.
  • control method for a robot in this embodiment includes operations S401 to S411.
  • the robot is controlled to move to the target waiting position corresponding to the target elevator, that is, the point E position.
  • the robot determines the current movable space according to the collected laser data.
  • a vector composed of the current movable space point and the center point of the robot is determined to obtain a first vector, wherein the current movable space point can be P1 or P2, and the vector composed of the current movable space point and the center point of the robot is obtained Can include vector OP1 or vector OP2.
  • a vector cross product method is used to determine whether there is an intersection between the first vector and the vector inside the elevator door, where the vector inside the elevator door may be the vector G1G4. If the intersection point exists, operation S405 is performed. If the intersection point does not exist, operation S410 is performed.
  • the robot determines the movable space based on the laser data collected at regular intervals.
  • a space between the target point and the movable space point is determined.
  • the space vector of the relationship is n, and n space vectors are obtained.
  • the movable space point of the movable space can include point P1
  • the target point can be the center point O of the robot
  • one of the space vectors can be vector OP1
  • the specified point can be AB points on the line.
  • target vectors that intersect with the equivalent coordinate vectors of the elevator doors are selected from n space vectors to obtain a target vector set, where the equivalent coordinate vectors of the elevator doors may include vectors G1G4.
  • operation S408 for each target vector in the target vector set, it is determined whether the distance from the intersection point between the target vector and the equivalent coordinate vector to the target movable space point satisfies the preset distance condition. When the distance from the intersection point between the target vector and the equivalent coordinate vector to the target movable space point meets the preset distance condition, operation S409 is performed; If the distance of the moving space point does not meet the preset distance condition, operation S410 is performed.
  • the robot stopping in the elevator door groove area may cause jamming. Therefore, when the robot reaches the AB line in front of the elevator door, it needs Determine whether the interior space of the elevator meets the conditions for robot entry. Only when the internal space of the elevator meets the conditions for the robot to enter, the robot will continue to perform the task. Otherwise, the task of entering the elevator will be canceled to avoid unnecessary squeezing of the elevator, which will cause the task execution time to be too long and affect the elevator ride experience.
  • the above-mentioned laser data includes angle data of the laser point; the above-mentioned determination of the movable space based on the laser data collected by the above-mentioned robot includes: determining the laser point that meets the preset angle threshold according to the angle data of the above-mentioned laser point, obtaining Target laser point set, wherein the above-mentioned preset angle threshold includes a movable space determined according to the laser points within the above-mentioned preset angle threshold, capable of covering the elevator area of the above-mentioned target elevator; extracting the above-mentioned target laser point from the above-mentioned laser data Collect corresponding laser data to obtain target laser data; determine the movable space of the target elevator based on the target laser data.
  • the angle data of the laser point may include, for example, the angle of the laser point relative to the origin of the coordinates in the robot coordinate system.
  • the preset angle threshold may include the maximum angle value on both sides of the robot, ensuring that the movable space obtained based on the laser point within the preset angle threshold range can cover the elevator area of the target elevator.
  • the target laser data is obtained by extracting laser data corresponding to the target laser point set from the laser data, and then the movable space is determined based on the target laser data. Since only laser points that can cover the internal area of the elevator are Laser data is processed, reducing the amount of data processing and helping to reduce the processing efficiency of the robot.
  • the target laser point set includes k target laser points, where k ⁇ 1; wherein, determining the movable space based on the target laser data includes: in the coordinate system of the robot, for the above For each target laser point in the target laser point set, determine the direction of the above-mentioned target laser point, and obtain the laser direction corresponding to the above-mentioned target laser point; determine the boundary value of the movable space point in the above-mentioned laser direction, and obtain k of the above-mentioned movable space points. Boundary values of moving space points; determine the above-mentioned movable space based on k boundary values of the above-mentioned movable space points.
  • Figure 5 schematically shows a flow chart of a movable space determination method according to an embodiment of the present disclosure.
  • the method in this embodiment includes operations S501 to S506.
  • laser points that meet a preset angle threshold are determined according to the angle data of the laser points in the laser data, and a target laser point set is obtained.
  • laser data corresponding to the target laser point set is extracted from the laser data to obtain target laser data.
  • the movable spatial point boundary value in the j-th laser direction is determined, and the j-th movable spatial point boundary value is obtained.
  • each target laser point in the target laser point set is traversed to obtain multiple Movable space point boundary value.
  • the movable space is determined according to the plurality of movable space point boundary values.
  • the above-mentioned determination of the movable spatial point boundary value in the above-mentioned laser direction includes: operation S1, determining the angle of the above-mentioned laser direction relative to the reference axis in the coordinate system of the above-mentioned robot to obtain the target angle; operation S2, For the i-th target laser point in the above-mentioned target laser point set, when the above-mentioned i-th target laser point is rotated by the above-mentioned target angle, determine the i-th lateral distance corresponding to the above-mentioned i-th target laser point, where 1 ⁇ i ⁇ k ; Operation S3, when the i-th lateral distance is less than the preset lateral distance threshold, obtain the ordinate value of the i-th target laser point, where the preset lateral distance threshold represents the lateral obstacle reference range of the robot ; Operation S4, when the ordinate value of the i-th target laser point is less than the current feasible boundary threshold
  • Figure 6 schematically shows a flow chart of a movable space point boundary value determination method according to an embodiment of the present disclosure.
  • the method for determining the boundary value of the movable spatial point in the j-th laser direction includes operations S601 to S608.
  • the target laser points in the target laser point set are traversed in order, and for the current target laser point in the target laser point set, when the current target laser point is rotated by the jth target angle, the current target laser point corresponding to the current target laser point is determined. Lateral distance.
  • operation S603 it is determined whether the current lateral distance is less than a preset lateral distance threshold, where the preset lateral distance threshold represents the lateral obstacle reference range of the robot.
  • operation S604 is performed; If the lateral distance is greater than or equal to the preset lateral distance threshold, operation S602 is performed.
  • operation S605 it is determined whether the ordinate value of the current target laser point is less than the current feasible boundary threshold. If the ordinate value of the current target laser point is less than the current feasible boundary threshold, perform operation S606; if the ordinate value of the current target laser point is greater than or equal to the current feasible boundary threshold, perform operation S602.
  • the current feasible boundary threshold is updated using the ordinate value of the current target laser point to obtain an updated feasible boundary threshold.
  • operations S602 to S606 are executed in a loop to update the current feasible boundary threshold until the target laser points in the target laser point set are traversed, then the update of the current feasible boundary threshold is completed, and the final feasible boundary threshold is obtained.
  • the final feasible boundary threshold is determined to be the movable spatial point boundary value in the j-th laser direction.
  • constructing a movable space based on laser data has the advantages of high tolerance to positioning deviations and strong traffic capacity in the scenario of a narrow passage leading to an elevator.
  • the above-mentioned control method for the robot further includes: determining an extension vector used to characterize the spatial relationship between the target extension point and the center equivalent point of the above-mentioned target elevator, wherein the above-mentioned target extension point is the above-mentioned target A point extending a preset length in the negative direction of the longitudinal axis; when the above-mentioned extension vector and the above-mentioned equivalent coordinate vector do not intersect, it is determined that the above-mentioned robot has completely passed the above-mentioned elevator door and entered the above-mentioned target elevator.
  • the space between the tail of the robot and the elevator door needs to be sufficient for passengers to enter and exit the elevator.
  • Figure 7 schematically shows a schematic diagram of an elevator area including a target extension point according to an embodiment of the present disclosure.
  • Figure 8 schematically shows a flow chart of a method for determining whether a robot has completely entered an elevator according to an embodiment of the present disclosure.
  • the method for determining that the robot has completely entered the elevator in this embodiment includes operations S801 to S808.
  • vectors B1Gt and B2Gt are determined.
  • operation S802 it is determined whether there is an intersection between the vectors B1Gt, B2Gt and the vector G1G4.
  • operation S803 is performed; when it is determined that there is no intersection between the vectors B1Gt, B2Gt and the vector G1G4, operation S808 is performed.
  • operation S803 it is determined whether the number of intersection points is 2. When the number of intersection points is 2, operations S804 to S805 are performed; when the number of intersection points is not 2, operations S806 to S807 are performed.
  • the maximum value of L1 and L2 is determined to be L, so that the forward target point is determined using the L value, and the robot is controlled to move according to the forward target point.
  • the distance from the point corresponding to the intersection vector to the vector G1G4 is determined to be L, so as to determine the forward target point according to the L value, and control the robot to move according to the forward target point.
  • L is the distance between the robot tail B1B2 that has not yet entered the elevator. The maximum length.
  • the above control method for a robot further includes: before controlling the robot to enter the target elevator through the elevator door, determining a forward target from the target movable space point according to the target vector set point, where the direction of the forward target point is the forward direction of the robot.
  • the laser data in the embodiment of the present disclosure is acquired at regular intervals.
  • the moving space and forward target point are also determined periodically. Therefore, the method of the present disclosure determines the movable space based on laser data at regular intervals and determines the forward target point.
  • the above-mentioned target vector set includes m above-mentioned target vectors, m ⁇ 2; wherein, the above-mentioned determining the forward target point from the above-mentioned target movable space point according to the above-mentioned target vector set includes: targeting the above-mentioned target vector For each target vector in the set, determine the angle between the above-mentioned target vector and the reference vector, and obtain the vector angle value corresponding to the above-mentioned target vector; according to the distance from the above-mentioned target extension point to the above-mentioned equivalent coordinate vector, the angle corresponding to the above-mentioned target vector
  • the vector angle value and the rotation radius of the above-mentioned robot determine the reference value; when the line segment length of the above-mentioned target vector meets the reference value, determine the movable space point with the above-mentioned target as the alternative forward target point; from the alternative forward target point Determine the candidate forward target point
  • the calculation formula for determining the reference value based on the distance from the target extension point to the equivalent coordinate vector, the vector angle value corresponding to the target vector, and the rotation radius of the robot is as follows: L/cos ⁇ +R, where, L is the distance from the target extension point to the equivalent coordinate vector, that is, the maximum length of the robot tail B1B2 before entering the elevator; ⁇ is the angle value of the vector corresponding to the target vector; R is the rotation radius of the robot.
  • FIG. 9 schematically shows a flowchart of a method for determining an alternative forward target point according to an embodiment of the present disclosure.
  • the determination method in this embodiment includes operations S901 to operation 907.
  • the reference value is determined based on the distance from the target extension point to the equivalent coordinate vector, the vector angle value corresponding to the target vector, and the rotation radius of the robot.
  • operation S903 it is determined whether the line segment length of the target vector satisfies the reference value.
  • operation S904 is performed; when the line segment length of the target vector does not meet the reference value, operation S905 is performed.
  • the target movable space point is determined to be the candidate forward target point, where the target movable space point corresponds to the target vector, and then operation S906 is performed.
  • operation S905 it is determined that the target movable space point is not the candidate forward target point, wherein the target movable space point corresponds to the target vector, and then operation S906 is performed.
  • each target vector in the target vector set is traversed, and operations S901 to S905 are executed in a loop to obtain multiple candidate forward target points.
  • a candidate forward target point corresponding to the minimum vector angle value is determined from a plurality of candidate forward target points, and a forward target point is obtained.
  • the above-mentioned target vector set includes m above-mentioned target vectors, m ⁇ 2; wherein, the above-mentioned determining the forward target point from the above-mentioned target movable space point according to the above-mentioned target vector set includes: targeting the above-mentioned target vector For each target vector in the set, determine the angle between the above target vector and the reference vector, obtain the absolute value of the angle corresponding to the above target vector, and finally obtain m absolute values of the angle, where the above reference vector represents the above target point The vector of the spatial relationship with the center equivalent point of the above-mentioned target elevator; according to the above-mentioned m absolute values of the included angles, the above-mentioned forward target point is determined from the above-mentioned target movable space points.
  • determining the forward target point from the target movable space point based on the m absolute values of the included angles includes: determining the absolute value of the smallest included angle from the m absolute values of the included angles. , obtain the absolute value of the target angle; determine the movable space point corresponding to the absolute value of the target angle from the above-mentioned target movable space points, and obtain the above-mentioned forward target point.
  • the forward target point is flexibly selected according to the movable space and the reference target point to improve the success rate of the robot entering the elevator.
  • traverse the movable space points determine whether the vectors composed of the robot origin and the movable space points and the vector G1G4 intersect, and find the movable space point with the smallest absolute value of the angle to the reference vector among the intersecting movable space points.
  • the spatial point is used as a forward target point to improve the smoothness of the robot entering the elevator.
  • the above method further includes: according to the forward target point, controlling the robot to enter the target elevator through the elevator door along the forward target point method.
  • the above-mentioned control method for a robot further includes: when the feasible distance in the direction where the above-mentioned forward target point is located is greater than or equal to a preset value, controlling the above-mentioned robot along the direction where the above-mentioned forward target point is located. direction movement, where the above default value It is determined based on the speed of the above-mentioned robot, the acceleration and distance compensation value of the above-mentioned robot.
  • the preset value s can be calculated using the following formula: v 2 /2a+s 0 ; where v represents the traveling speed of the robot, a represents the acceleration, s 0 is the distance supplementary value, and s 0 can be based on the actual Application scenarios and robot control accuracy configuration
  • the robot when the feasible distance in the direction of the forward target point is less than a preset value, the robot is controlled to decelerate in time to prevent a collision with an obstacle.
  • a commonly used path tracking algorithm is used to calculate the traveling speed of the robot.
  • the robot before entering the elevator, the robot first determines whether the elevator door is open. Only when the elevator door is open, the robot will perform the task of entering the elevator. Then based on the laser data collected by the robot, the longest distance that the robot can travel in all directions within the covered elevator space is determined, thereby constructing a movable space.
  • the space vector used to represent the spatial relationship between the target point and the movable space point is determined, and multiple space vectors are obtained, and then based on multiple The space vector determines whether the movable space meets the entry conditions for the robot. Only when the movable space meets the entry conditions will the robot continue to perform the task of entering the elevator. If the movable space does not meet the entry conditions, the robot will not enter the elevator to avoid The robot squeezes into the elevator unnecessarily, resulting in a poor elevator experience. It also helps improve the success rate of the robot entering the elevator.
  • the present disclosure also provides a control device for a robot.
  • the device will be described in detail below with reference to FIG. 10 .
  • FIG. 10 schematically shows a structural block diagram of a control device for a robot according to an embodiment of the present disclosure.
  • the control device 1000 for a robot in this embodiment includes a first The control module 1010, the first determination module 1020, the second determination module 1030 and the second control module 1040.
  • the first control module 1010 is used to control the robot to move to the target waiting position corresponding to the target elevator.
  • the first control module 1010 may be configured to perform the operation S210 described above, which will not be described again here.
  • the first determination module 1020 is configured to determine the movable space based on the laser data collected by the robot when it is determined that the elevator door of the target elevator is open, wherein the movable space is formed by n movable space points. Among them, n ⁇ 1. In an embodiment, the first determination module 1020 may be configured to perform the operation S220 described above, which will not be described again here.
  • the second determination module 1030 is configured to determine, for each of the n movable space points, a space vector used to characterize the spatial relationship between the target point and the movable space point, and obtain the n space vectors. , where the above target point is located on the above robot. In an embodiment, the second determination module 1030 may be configured to perform the operation S230 described above, which will not be described again here.
  • the second control module 1040 is used to control the movement state of the robot according to the n space vectors.
  • the second control module 1040 may be configured to perform the operation S240 described above, which will not be described again here.
  • the above-mentioned second control module includes: a screening sub-module and a control sub-module.
  • the screening submodule is used to screen the target vectors that intersect with the equivalent coordinate vectors of the above-mentioned stair doors from the n above-mentioned space vectors when the above-mentioned robot moves to a designated point, and obtain a target vector set, wherein the above-mentioned equivalent coordinates
  • the vector is a coordinate vector used to represent the spatial relationship between equivalent points on the above-mentioned elevator door.
  • the above-mentioned specified point is located outside the above-mentioned target elevator and is close to the elevator door groove of the above-mentioned target elevator.
  • the control submodule is used to control the above-mentioned robot to enter the above-mentioned target elevator through the above-mentioned elevator door when the distance from the intersection point between the above-mentioned target vector and the above-mentioned equivalent coordinate vector to the target movable space point meets the preset distance condition, wherein, the above-mentioned target movable space point corresponds to the above-mentioned target vector.
  • the above-mentioned laser data includes angle data of the laser point.
  • the above-mentioned first determination module includes: a first determination sub-module, an extraction sub-module and a second determination sub-module.
  • the first determination sub-module is used to determine the laser points that meet the preset angle threshold according to the angle data of the above-mentioned laser points, and obtain the target laser point set, wherein the above-mentioned preset angle threshold includes laser points based on the above-mentioned preset angle threshold.
  • the determined movable space can cover the elevator area of the above-mentioned target elevator.
  • An extraction module is used to extract laser data corresponding to the target laser point set from the above laser data to obtain target laser data.
  • the second determination sub-module is used to determine the movable space according to the target laser data.
  • the above target laser point set includes k target laser points, where k ⁇ 1.
  • the above-mentioned second determination sub-module includes: a first determination unit, a second determination unit and a third determination unit.
  • the first determination unit is configured to determine the direction of the target laser point for each target laser point in the target laser point set in the coordinate system of the robot, and obtain the laser direction corresponding to the target laser point.
  • the second determination unit is used to determine the boundary value of the movable space point in the laser direction, and obtain the k boundary values of the movable space point.
  • the third determination unit is used to determine the movable space based on k boundary values of the movable space points.
  • the above-mentioned second determination unit includes: a first determination sub-unit, a second determination sub-unit, an acquisition sub-unit, an update sub-unit, a traversal sub-unit and a third determination sub-unit.
  • the first determination subunit is used to determine the angle of the laser direction relative to the reference axis in the coordinate system of the robot to obtain the target angle.
  • the second determination sub-unit is used to determine, for the i-th target laser point in the above-mentioned target laser point set, when the above-mentioned i-th target laser point rotates the above-mentioned target angle, determine the same as the above-mentioned The i-th lateral distance corresponding to the i-th target laser point, where 1 ⁇ i ⁇ k.
  • Obtaining subunit configured to obtain the ordinate value of the i-th target laser point when the i-th lateral distance is less than a preset lateral distance threshold, wherein the preset lateral distance threshold represents the lateral obstacles of the robot Reference range.
  • Update subunit used to update the above-mentioned current feasible boundary threshold using the ordinate value of the i-th target laser point when the ordinate value of the above-mentioned i-th target laser point is less than the current feasible boundary threshold, and obtain the updated feasible boundary threshold.
  • the traversal subunit is used to traverse the above-mentioned target laser point set, cyclically perform the operations of the second determination subunit, the acquisition subunit and the update subunit to cyclically update the current feasible boundary threshold until the target in the above-mentioned target laser point set is traversed After the laser point, the update of the current feasible boundary threshold ends and the final feasible boundary threshold is obtained.
  • the third determination subunit is used to determine the final feasible boundary threshold as the movable spatial point boundary value in the laser direction.
  • control device for a robot further includes: a third determination module and a fourth determination module.
  • the third determination module is used to determine the extension vector used to characterize the spatial relationship between the target extension point and the central equivalent point of the above-mentioned target elevator, wherein the above-mentioned target extension point is a preset length of the above-mentioned target point extending in the negative direction of the longitudinal axis. The last point.
  • the fourth determination module is used to determine that the robot has completely passed through the elevator door and entered the target elevator when the extension vector and the equivalent coordinate vector do not intersect.
  • control device for a robot further includes a fifth determination module.
  • the fifth determination module is used to determine the forward target point from the target movable space point according to the target vector set before controlling the robot to enter the target elevator through the elevator door, wherein the forward target point is located
  • the direction of is the forward direction of the above-mentioned robot.
  • the above-mentioned target vector set includes m above-mentioned target vectors, m ⁇ 2.
  • the above-mentioned fifth determination module includes: a third determination sub-module and a fourth determination sub-module.
  • the third determination sub-module is used to determine the angle of the above target vector relative to the reference vector for each target vector in the above target vector set, obtain the absolute value of the angle corresponding to the above target vector, and finally obtain m absolute values of the included angles. value, wherein the above-mentioned reference vector is a vector representing the spatial relationship between the above-mentioned target point and the central equivalent point of the above-mentioned target elevator.
  • the fourth determination sub-module is used to determine the forward target point from the target movable space point based on the absolute values of the m included angles.
  • the above-mentioned fourth determination sub-module includes: a fourth determination unit and a fifth determination unit.
  • the fourth determination unit is used to determine the smallest absolute value of the included angle from the above-mentioned m absolute values of the included angle, and obtain the absolute value of the target included angle.
  • the fifth determination unit is used to determine the movable space point corresponding to the absolute value of the target angle from the target movable space point to obtain the forward target point.
  • the above-mentioned target vector set includes m above-mentioned target vectors, m ⁇ 2
  • the above-mentioned fifth determination module includes: the above-mentioned fifth determination sub-module, sixth determination sub-module, seventh determination sub-module and eighth determination sub-module.
  • the fifth determination sub-module is used to determine the angle of the target vector relative to the reference vector for each target vector in the target vector set, and obtain the vector angle value corresponding to the target vector.
  • the sixth determination sub-module is used to determine the reference value based on the distance from the target extension point to the equivalent coordinate vector, the vector angle value corresponding to the target vector, and the rotation radius of the robot.
  • the seventh determination sub-module is used to determine the movable space point related to the target as an alternative forward target point when the line segment length of the target vector satisfies the reference value.
  • the eighth determination sub-module is used to determine the candidate forward target point corresponding to the minimum vector angle value from the candidate forward target points, and obtain the above-mentioned forward target point.
  • the above-mentioned control submodule is also used to control the above-mentioned forward target point
  • the above-mentioned robot is controlled to move in the direction of the above-mentioned forward target point, wherein the above-mentioned preset value is based on the speed of the above-mentioned robot, the acceleration of the above-mentioned robot and the distance compensation value.
  • modules, sub-modules, units, sub-units may be implemented in one module. Any one or more of the modules, sub-modules, units, and sub-units according to the embodiments of the present disclosure may be split into multiple modules for implementation.
  • any one or more of the modules, sub-modules, units, and sub-units according to embodiments of the present disclosure may be at least partially implemented as hardware circuits, such as field programmable gate arrays (FPGAs), programmable logic arrays (PLA), System-on-a-chip, system-on-substrate, system-on-package, application-specific integrated circuit (ASIC), or any other reasonable means of integrating or packaging circuits that can be implemented in hardware or firmware, or in a combination of software, hardware, and firmware Any one of these implementation methods or an appropriate combination of any of them.
  • FPGAs field programmable gate arrays
  • PLA programmable logic arrays
  • ASIC application-specific integrated circuit
  • one or more of the modules, sub-modules, units, and sub-units according to the embodiments of the present disclosure may be at least partially implemented as a computer program module, and when the computer program module is executed, corresponding functions may be performed.
  • any one of the first control module 1010, the first determination module 1020, the second determination module 1030 and the second control module 1040 can be combined and implemented in one module/unit/subunit, or any one module/ A unit/subunit can be split into multiple modules/units/subunits.
  • at least part of the functionality of one or more of these modules/units/subunits may be combined with at least part of the functionality of other modules/units/subunits and combined in one module/unit/subunit realized in.
  • at least one of the first control module 1010, the first determination module 1020, the second determination module 1030 and the second control module 1040 may be at least partially implemented as a hardware circuit, such as a field programmable gate array.
  • FPGA programmable logic array
  • PLA programmable logic array
  • ASIC application specific integrated circuit
  • FIG. 11 schematically shows a block diagram of an electronic device suitable for implementing the above-described method according to an embodiment of the present disclosure.
  • the electronic device shown in FIG. 11 is only an example and should not impose any limitations on the functions and scope of use of the embodiments of the present disclosure.
  • an electronic device 1100 includes a processor 1101 that can be loaded into a random access memory (RAM) 1103 according to a program stored in a read-only memory (ROM) 1102 or from a storage part 1108 program to perform various appropriate actions and processes.
  • processor 1101 may include, for example, a general purpose microprocessor (eg, a CPU), an instruction set processor and/or associated chipset, and/or a special purpose microprocessor (eg, an application specific integrated circuit (ASIC)), among others.
  • Processor 1101 may also include onboard memory for caching purposes.
  • the processor 1101 may include a single processing unit or multiple processing units for performing different actions of the method flow according to the embodiment of the present disclosure.
  • the processor 1101, ROM 1102 and RAM 1103 are connected to each other through a bus 1104.
  • the processor 1101 performs various operations according to the method flow of the embodiment of the present disclosure by executing programs in the ROM 1102 and/or RAM 1103. It should be noted that the program may also be stored in one or more memories other than ROM 1102 and RAM 1103.
  • the processor 1101 may also perform various operations according to the method flow of embodiments of the present disclosure by executing programs stored in the one or more memories.
  • the electronic device 1100 may further include an input/output (I/O) interface 1105 that is also connected to the bus 1104 .
  • System 1100 may also include one or more of the following components connected to I/O interface 1105: an input portion 1106 including a keyboard, mouse, etc.; including a device such as a cathode ray tube (CRT), a liquid crystal display (LCD), etc.; and a speaker.
  • an output section 1107, etc. a storage section 1108 including a hard disk, etc.
  • a communication section 1109 including a network interface card such as a LAN card, a modem, etc.
  • the communication section 1109 performs communication processing via a network such as the Internet.
  • Driver 1110 is also connected to I/O interface 1105 as needed.
  • Removable media 1111 such as magnetic disks, optical disks, magneto-optical disks, A semiconductor memory or the like is installed on the drive 1110 as necessary so that a computer program read therefrom is installed into the storage section 1108 as needed.
  • the method flow according to the embodiments of the present disclosure may be implemented as a computer software program.
  • embodiments of the present disclosure include a computer program product including a computer program carried on a computer-readable storage medium, the computer program containing program code for performing the method illustrated in the flowchart.
  • the computer program may be downloaded and installed from the network via communication portion 1109 and/or installed from removable media 1111 .
  • the computer program is executed by the processor 1101, the above-described functions defined in the system of the embodiment of the present disclosure are performed.
  • the systems, devices, devices, modules, units, etc. described above may be implemented by computer program modules.
  • the present disclosure also provides a computer-readable storage medium.
  • the computer-readable storage medium may be included in the device/device/system described in the above embodiments; it may also exist independently without being assembled into the device/system. in the device/system.
  • the above computer-readable storage medium carries one or more programs. When the above one or more programs are executed, the method according to the embodiment of the present disclosure is implemented.
  • the computer-readable storage medium may be a non-volatile computer-readable storage medium. Examples may include but are not limited to: portable computer disks, hard disks, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), portable compact disk read-only memory (CD-ROM), ROM), optical storage device, magnetic storage device, or any suitable combination of the above.
  • a computer-readable storage medium may be any tangible medium that contains or stores a program for use by or in connection with an instruction execution system, apparatus, or device.
  • the computer-readable storage medium may include one or more memories other than ROM 1102 and/or RAM 1103 and/or ROM 1102 and RAM 1103 described above.
  • each block in the flowchart or block diagrams may represent a module, segment, or portion of code that contains one or more components used to implement the provisions Executable instructions for logical functions.
  • the functions noted in the block may occur out of the order noted in the figures. For example, two blocks shown one after another may actually execute substantially in parallel, or they may sometimes execute in the reverse order, depending on the functionality involved.
  • each block in the block diagram or flowchart illustration, and combinations of blocks in the block diagram or flowchart illustration can be implemented by special purpose hardware-based systems that perform the specified functions or operations, or may be implemented by special purpose hardware-based systems that perform the specified functions or operations. Achieved by a combination of specialized hardware and computer instructions.

Landscapes

  • Engineering & Computer Science (AREA)
  • Aviation & Aerospace Engineering (AREA)
  • Radar, Positioning & Navigation (AREA)
  • Remote Sensing (AREA)
  • Physics & Mathematics (AREA)
  • General Physics & Mathematics (AREA)
  • Automation & Control Theory (AREA)
  • Manipulator (AREA)

Abstract

一种用于机器人（101）的控制方法，包括：控制机器人（101）移动至与目标电梯（102、103）对应的目标候梯位置（S210）；在确定目标电梯（102、103）的梯门开启的情况下，根据由机器人（101）采集的激光数据确定可移动空间，其中，可移动空间由n个可移动空间点围合形成，其中，n≥1（S220）；针对n个可移动空间点中的每个可移动空间点，确定用于表征目标点与可移动空间点之间空间关系的空间向量，得到n个空间向量，其中，目标点位于机器人（101）上（S230）；以及根据n个空间向量控制机器人（101）的移动状态（S240）。

Description

用于机器人的控制方法、装置、电子设备及存储介质 技术领域
本公开涉及智能机器人技术领域，更具体地，涉及一种用于机器人的控制方法方法、装置、电子设备、介质和程序产品。
背景技术
随着人工智能、自动控制、通信和计算机技术的快速发展，机器人被越来越多地应用于工农业生产、建筑、物流和日常生活等诸多领域。机器人在实际应用中通常存在进出电梯的场景，在该场景下通常要求机器人能够根据电梯内部的空间大小找到停车点，以顺利地完成进电梯任务。目前，机器人进入电梯的方法一般将打在电梯内部的激光点组成的包络以一定比例进行缩小以得到机器人的可移动空间，然后控制机器人进入电梯。
在实现本公开构思的过程中，发明人发现相关技术中至少存在如下问题：在激光点形成的包络不规则时，采用上述方法得到的机器人可移动空间的精确度较低，从而影响机器人进入电梯的顺畅度和成功率。
发明内容
有鉴于此，本公开提供了一种用于机器人的控制方法、装置、电子设备、介质和程序产品。
本公开的一个方面提供了一种用于机器人的控制方法，包括：
控制机器人移动至与目标电梯对应的目标候梯位置；
在确定上述目标电梯的梯门开启的情况下，根据由上述机器人采集的激光数据确定可移动空间，其中，上述可移动空间由n个可移动空间点围合形成，其中，n≥1；
针对上述n个可移动空间点中的每个可移动空间点，确定用于表征目标点与上述可移动空间点之间空间关系的空间向量，得到n个上述空间向量，其中，上述目标点位于上述机器人上；以及
根据n个上述空间向量控制上述机器人的移动状态。
根据本公开的实施例，上述根据n个上述空间向量控制上述机器人的移动状态包括：
在上述机器人移动至指定点的情况下，从n个上述空间向量中筛选与上述梯门的等效坐标向量相交的目标向量，得到目标向量集，其中，上述等效坐标向量用于表征上述梯门上的等效点之间空间关系的坐标向量，上述指定点位于上述目标电梯外部，且靠近上述目标电梯的梯门凹槽；
在上述目标向量和上述等效坐标向量之间的相交点至目标可移动空间点的距离满足预设距离条件的情况下，控制上述机器人通过上述梯门进入上述目标电梯，其中，上述目标可移动空间点与上述目标向量对应。
根据本公开的实施例，上述激光数据包括激光点的角度数据；
上述根据由上述机器人采集的激光数据确定可移动空间包括：
根据上述激光点的角度数据确定满足预设角度阈值的激光点，得到目标激光点集，其中，上述预设角度阈值包括根据在上述预设角度阈值内的激光点确定的可移动空间，能够覆盖上述目标电梯的电梯区域；
从上述激光数据中提取与上述目标激光点集对应的激光数据，得到目标激光数据；
根据上述目标激光数据确定上述可移动空间。
根据本公开的实施例，上述目标激光点集包括k个目标激光点，其中，k≥1；
其中，上述根据上述目标激光数据确定上述可移动空间包括：
在上述机器人的坐标系下，针对上述目标激光点集中的每个目标激光点，确定上述目标激光点所在的方向，得到与上述目标激光点对 应的激光方向；
确定在上述激光方向上的可移动空间点边界值，得到k个上述可移动空间点边界值；
根据k个上述可移动空间点边界值确定上述可移动空间。
根据本公开的实施例，上述确定在上述激光方向上的可移动空间点边界值包括：
操作S1，确定上述激光方向相对于上述机器人的坐标系中基准轴的角度，得到目标角度；
操作S2，针对上述目标激光点集中的第i目标激光点，在上述第i目标激光点旋转上述目标角度的情况下，确定与上述第i目标激光点对应的第i横向距离，其中，1≤i≤k；
操作S3，在上述第i横向距离小于预设横向距离阈值的情况下，获取上述第i目标激光点的纵坐标值，其中，上述预设横向距离阈值表征上述机器人在横向的障碍物参考范围；
操作S4，在上述第i目标激光点的纵坐标值小于当前可行边界阈值的情况下，利用上述第i目标激光点的纵坐标值更新上述当前可行边界阈值，得到更新后的可行边界阈值；
操作S5，遍历上述目标激光点集，循环执行操作S2-操作S4以循环更新当前可行边界阈值，直到遍历上述目标激光点集中的目标激光点之后，结束对当前可行边界阈值的更新，得到最终可行边界阈值；
操作S6，确定上述最终可行边界阈值为在上述激光方向上的可移动空间点边界值。
根据本公开的实施例，上述用于机器人的控制方法还包括：
确定用于表征目标延长点与上述目标电梯的中心等效点之间空间关系的延长向量，其中，上述目标延长点为上述目标点向纵轴负方向延伸预设长度后的点；
在上述延长向量与上述等效坐标向量之间不相交的情况下，确定上述机器人完全通过上述梯门，并进入上述目标电梯内。
根据本公开的实施例，上述用于机器人的控制方法还包括：
在上述控制上述机器人通过上述梯门进入上述目标电梯之前，根据上述目标向量集，从上述目标可移动空间点中确定前向目标点，其中，上述前向目标点所在的方向为上述机器人的前进方向。
根据本公开的实施例，上述目标向量集包括m个上述目标向量，m≥1；
其中，上述根据上述目标向量集，从上述目标可移动空间点中确定前向目标点包括：
针对上述目标向量集中的每个目标向量，确定上述目标向量相对于参考向量的夹角，得到与上述目标向量对应的夹角绝对值，最终得到m个夹角绝对值，其中，上述参考向量为表征上述目标点与上述目标电梯的中心等效点之间空间关系的向量；
根据上述m个夹角绝对值，从上述目标可移动空间点中确定上述前向目标点。
根据本公开的实施例，上述根据上述m个夹角绝对值，从上述目标可移动空间点中确定上述前向目标点包括：
从上述m个夹角绝对值中确定数值最小的夹角绝对值，得到目标夹角绝对值；
从上述目标可移动空间点中，确定与上述目标夹角绝对值对应的可移动空间点，得到上述前向目标点。
根据本公开的实施例，上述目标向量集包括m个上述目标向量，m≥1；
其中，上述根据上述目标向量集，从上述目标可移动空间点中确定前向目标点包括：
针对上述目标向量集中的每个目标向量，确定上述目标向量相对于参考向量的夹角，得到与上述目标向量对应的向量夹角值；
根据上述目标延长点到上述等效坐标向量的距离、与上述目标向量对应的向量夹角值和上述机器人的旋转半径确定参考值；
在上述目标向量的线段长度满足参考值的情况下，确定与上述目标可移动空间点为备选前向目标点；
从备选前向目标点中确定与最小向量夹角值对应的备选前向目标点，得到上述前向目标点。
根据本公开的实施例，上述用于机器人的控制方法还包括：
在上述前向目标点所在的方向上的可行距离大于等于预设值的情况下，控制上述机器人沿上述前向目标点所在的方向移动，其中，上述预设值根据上述机器人的速度、上述机器人的加速度和距离补偿值确定。
本公开的另一个方面提供了一种用于机器人的控制装置，包括：
第一控制模块，用于控制机器人移动至与目标电梯对应的目标候梯位置；
第一确定模块，用于在确定上述目标电梯的梯门开启的情况下，根据由上述机器人采集的激光数据确定可移动空间，其中，上述可移动空间由n个可移动空间点围合形成，其中，n≥1；
第二确定模块，用于针对上述n个可移动空间点中的每个可移动空间点，确定用于表征目标点与上述可移动空间点之间空间关系的空间向量，得到n个上述空间向量，其中，上述目标点位于上述机器人上；以及
第二控制模块，用于根据n个上述空间向量控制上述机器人的移动状态。
本公开的另一个方面提供了一种电子设备，包括：一个或多个处理器；存储器，用于存储一个或多个程序，其中，当上述一个或多个程序被上述一个或多个处理器执行时，使得一个或多个处理器执行上述用于机器人的控制方法。
本公开的另一方面提供了一种计算机可读存储介质，存储有计算机可执行指令，所述指令在被执行时用于实现本公开实施例所述的方法。
本公开的另一方面提供了一种计算机程序，所述计算机程序包括计算机可执行指令，所述指令在被执行时用于实现本公开实施例所述的方法。
根据本公开的实施例，因为采用了控制机器人移动至与目标电梯对应的目标候梯位置，然后在目标电梯的梯门开启的情况下，根据机器人采集的激光数据确定可移动空间，之后针对可移动空间的每个可移动空间点，确定用于表征目标点与可移动空间点之间空间关系的空间向量，得到n个空间向量，之后根据n个空间向量控制机器人的移动状态的技术手段，所以至少部分地克服了在包络不规则时缩放效果较差，从而影响机器人进入电梯的性能的技术问题，进而达到了提高机器人进入电梯的顺畅度和成功率的技术效果。
附图说明
通过以下参照附图对本公开实施例的描述，本公开的上述以及其他目的、特征和优点将更为清楚，在附图中：
图1示意性示出了根据本公开实施例的可以应用用于机器人的控制方法和装置的示例性系统架构；
图2示意性示出了根据本公开实施例的用于机器人的控制方法的流程图；
图3示意性示出了根据本公开实施例的目标电梯区域的示意图；
图4示意性示出了根据本公开另一实施例的用于机器人的控制方法的流程图；
图5示意性示出了根据本公开实施例的可移动空间确定方法的流程图；
图6示意性示出了根据本公开实施例的可移动空间点边界值确定方法的流程图；
图7示意性示出了根据本公开实施例的包含目标延长点的电梯区域示意图；
图8示意性示出了根据本公开实施例的机器人完全进入电梯确定方法的流程图；
图9示意性示出了根据本公开实施例的备选前向目标点的确定方法的流程图；
图10示意性示出了根据本公开实施例的用于机器人的控制装置的结构框图；以及
图11示意性示出了根据本公开实施例的适于实现上文描述的方法的电子设备的框图。
具体实施方式
以下，将参照附图来描述本公开的实施例。但是应该理解，这些描述只是示例性的，而并非要限制本公开的范围。在下面的详细描述中，为便于解释，阐述了许多具体的细节以提供对本公开实施例的全面理解。然而，明显地，一个或多个实施例在没有这些具体细节的情况下也可以被实施。此外，在以下说明中，省略了对公知结构和技术的描述，以避免不必要地混淆本公开的概念。
在此使用的术语仅仅是为了描述具体实施例，而并非意在限制本公开。在此使用的术语“包括”、“包含”等表明了所述特征、步骤、操作和/或部件的存在，但是并不排除存在或添加一个或多个其他特征、步骤、操作或部件。
在此使用的所有术语(包括技术和科学术语)具有本领域技术人员通常所理解的含义，除非另外定义。应注意，这里使用的术语应解释为具有与本说明书的上下文相一致的含义，而不应以理想化或过于刻板的方式来解释。
在使用类似于“A、B和C等中至少一个”这样的表述的情况下，一般来说应该按照本领域技术人员通常理解该表述的含义来予以解释(例如，“具有A、B和C中至少一个的系统”应包括但不限于单独具有A、单独具有B、单独具有C、具有A和B、具有A和C、具有B和C、和/或具有A、B、C的系统等)。
移动机器人在实际应用中通常存在进出电梯的场景，在该场景下通常要求机器人能够根据电梯内部的空间大小找到较优的停车点，以顺利的完成进电梯任务。
相关技术中，机器人进入电梯的技术通常将机器人打在电梯内部 的激光点组成的包络以一定比例进行缩小，以得到机器人的可移动空间，然后在该可移动空间内找到能够满足机器人进入的目标点控制机器人进入电梯。
但是，在实现本公开构思的过程中，发明人发现相关技术中至少存在如下问题：上述将机器人打在电梯内部的激光点组成的包络进行缩小以得到机器人可移动空间的方法，在包络不规则时缩放效果较差，从而会影响机器人进入电梯的性能。
有鉴于此，本公开针对以上技术问题提供了一种用于机器人的控制方法，包括：控制机器人移动至与目标电梯对应的目标候梯位置；在确定上述目标电梯的梯门开启的情况下，根据由上述机器人采集的激光数据确定可移动空间，其中，上述可移动空间由n个可移动空间点围合形成，其中，n≥1；针对上述n个可移动空间点中的每个可移动空间点，确定用于表征目标点与上述可移动空间点之间空间关系的空间向量，得到n个上述空间向量，其中，上述目标点位于上述机器人上；以及根据n个上述空间向量控制上述机器人的移动状态。
根据本公开的实施例，因为采用了控制机器人移动至与目标电梯对应的目标候梯位置，然后在目标电梯的梯门开启的情况下，根据机器人采集的激光数据确定可移动空间，之后针对可移动空间的每个可移动空间点，确定用于表征目标点与可移动空间点之间空间关系的空间向量，得到n个空间向量，之后根据n个空间向量控制机器人的移动状态的技术手段，所以至少部分地克服了在包络不规则时缩放效果较差，从而影响机器人进入电梯的性能的技术问题，进而达到了提高机器人进入电梯的顺畅度和成功率的技术效果。
图1示意性示出了根据本公开实施例的可以应用用于机器人的控制方法和装置的示例性系统架构100。需要注意的是，图1所示仅为可以应用本公开实施例的系统架构的示例，以帮助本领域技术人员理解本公开的技术内容，但并不意味着本公开实施例不可以用于其他设备、系统、环境或场景。
如图1所示，根据该实施例的系统架构100可以包括机器人101、 电梯102、103，网络104和控制中心105。网络104用以在机器人101、和控制中心105之间提供通信链路的介质。网络104可以包括各种连接类型，例如有线和/或无线通信链路等等。
操作人员可以使用控制中心105通过网络104向机器人101发送操作指令，以使得机器人101移动至电梯102、103中任一一个电梯(例如电梯102)的候梯位置，或者机器人101根据行驶任务移动至电梯102、103中任一一个电梯(例如电梯102)的候梯位置。然后在电梯102的梯门开启的情况下，机器人101根据采集的激光数据确定电梯102内的可移动空间，并判断电梯102内的可移动空间是否满足进入条件，在电梯102内的可移动空间满足进入条件时机器人101才会继续执行进电梯任务，在可移动空间不满足进入条件的情况下，机器人101不进入电梯，并结束进电梯任务。
控制中心105可以是提供各种控制指令的控制中心，例如，向机器人101发送巡检指令，向机器人101发送移动位置指令等。
需要说明的是，本公开实施例所提供的用于机器人的控制方法一般可以由机器人101执行。相应地，本公开实施例所提供的用于机器人的控制装置一般可以设置于机器人101中。本公开实施例所提供的用于机器人的控制方法也可以由不同于机器人101且能够与机器人101通信的服务器或服务器集群执行。相应地，本公开实施例所提供的用于机器人的控制装置也可以设置于不同于机器人101且能够与机器人101通信的服务器或服务器集群中。
例如，机器人101将采集的激光数据传输给服务器集群，然后服务器集群对激光数据进行分析，确定可移动空间，并判断可移动空间是否满足进梯条件，之后将分析结果发送给机器人101，以便于控制机器人101的移动状态。
以下将基于图1描述的场景，通过图2～图9对公开实施例的用于机器人的控制方法进行详细描述。
图2示意性示出了根据本公开实施例的用于机器人的控制方法的流程图。
如图2所示，该实施例的用于机器人的控制方法包括操作S210～S240。
在操作S210，控制机器人移动至与目标电梯对应的目标候梯位置。
根据本公开的实施例，机器人在进入新的作业场景中，需要扫描场景的全局地图或获取场景的全局地图，然后根据机器人在全局地图中的位置执行相应任务以进行自动作业。
根据本公开的实施例，全局地图中可以包括各个区域的位置，例如房间位置、电梯位置、进出口位置等。具体地，例如在全局地图中，电梯可以利用多边形来表征电梯的轮廓，以标识电梯门的位置。
根据本公开的实施例，机器人根据全局地图可以确定电梯位置和候梯地点，然后按照设定的指令移动至电梯门正前方且对电梯门方向一定距离，即目标候梯位置。
在操作S220，在确定上述目标电梯的梯门开启的情况下，根据由上述机器人采集的激光数据确定可移动空间，其中，上述可移动空间由n个可移动空间点围合形成，其中，n≥1。
根据本公开的实施例，机器人到达目标候梯位置后，需要判断目标电梯的梯门是否开启，在目标电梯的梯门开启的情况下，再根据机器人采集的激光数据确定可移动空间。
根据本公开的实施例，机器人采集的激光数据可以是经过滤波、稀疏化等预处理数据，并将预处理的数据转换到机器人坐标系下的数据。
在操作S230，针对上述n个可移动空间点中的每个可移动空间点，确定用于表征目标点与上述可移动空间点之间空间关系的空间向量，得到n个上述空间向量，其中，上述目标点位于上述机器人上。
根据本公开的实施例，目标点可以为机器人的中心点。空间向量可以是以目标点和可移动空间点为端点的向量。
在操作S240，根据n个上述空间向量控制上述机器人的移动状态。
根据本公开的实施例，机器人的移动状态可以包括保持在目标候梯位置不进入目标电梯，还可以包括通过目标电梯的梯门进入目标电梯。
根据本公开的实施例，因为采用了控制机器人移动至与目标电梯对应的目标候梯位置，然后在目标电梯的梯门开启的情况下，根据机器人采集的激光数据确定可移动空间，之后针对可移动空间的每个可移动空间点，确定用于表征目标点与可移动空间点之间空间关系的空间向量，得到n个空间向量，之后根据n个空间向量控制机器人的移动状态的技术手段，所以至少部分地克服了在包络不规则时缩放效果较差，从而影响机器人进入电梯的性能的技术问题，进而达到了提高机器人进入电梯的顺畅度和成功率的技术效果。
根据本公开的实施例，上述方法还包括：机器人根据采集的激光数据确定当前可移动空间，利用向量叉乘的方法判断当前可移动空间的空间点和机器人的中心点组成的向量，与梯门内侧的向量是否存在交点，若存在交点，则说明梯门开启。
根据本公开的实施例，上述方法还包括：机器人根据自身到梯门的距离，统计大于预设数值的激光射线数量来判断梯门是否开启。
根据本公开的实施例，在上述机器人移动至指定点的情况下，上述根据n个上述空间向量控制上述机器人的移动状态包括：从n个上述空间向量中筛选与上述梯门的等效坐标向量相交的目标向量，得到目标向量集，其中，上述等效坐标向量用于表征上述梯门上的等效点之间空间关系的坐标向量，上述指定点位于上述目标电梯外部，且靠近上述目标电梯的梯门凹槽；在上述目标向量和上述等效坐标向量之间的相交点至目标可移动空间点的距离满足预设距离条件的情况下，控制上述机器人通过上述梯门进入上述目标电梯，其中，上述目标可移动空间点与上述目标向量对应。
根据本公开的实施例，预设距离可以为f×R，其中，f为系数，R为机器人的旋转半径，一般情况下f应大于1。
根据本公开的实施例，在机器人移动至靠近梯门凹槽的指定点时，判断目标电梯内部是否满足进梯条件，满足进梯条件的情况下才执行进梯任务，避免机器人卡在电梯门凹槽位置。
根据本公开的实施例，上述方法还包括：在上述目标向量和上述等效坐标向量之间的相交点至目标可移动空间点的距离不满足预设距离条件的情况下，结束进梯任务。
在其中一个实施例中，例如目标电梯的轮廓为矩形，则利用矩形四个顶点的坐标标识目标电梯。机器人可以从全局地图中获取目标电梯的四个顶点坐标。
图3示意性示出了根据本公开实施例的目标电梯区域的示意图。
如图3所示，目标电梯的四个顶点分别为G1、G2、G3和G4，G1、G2、G3和G4组成的区域为目标电梯的梯内区域，点P1为电梯内部的可移动空间点，点P2为电梯外部的可移动空间点。点G1、G4、A和B组成的区域为电梯门凹槽区域，机器人的中心点为点O，目标候梯位置为E点。
图4示意性示出了根据本公开另一实施例的用于机器人的控制方法的流程图。
结合图3和图4所示，该实施例的用于机器人的控制方法包括操作S401～操作S411。
在操作S401，控制机器人移动至与目标电梯对应的目标候梯位置，即点E位置。
在操作S402，机器人根据采集的激光数据确定当前可移动空间。
在操作S403，确定当前可移动空间点和机器人的中心点组成的向量，得到第一向量，其中，当前可移动空间点可以为P1或P2，当前可移动空间点和机器人的中心点组成的向量可以包括向量OP1或向量OP2。
在操作S404，利用向量叉乘的方法判断第一向量与梯门内侧的向量是否存在交点，其中，梯门内侧的向量可以为向量G1G4。在存在交点的情况下，执行操作S405，在不存在交点的情况下，执行操作S410。
在操作S405，机器人根据定周期采集的激光数据确定可移动空间。
在操作S406，在机器人移动至指定点的情况下，针对可移动空间的每个可移动空间点，确定用于表征目标点与可移动空间点之间空间 关系的空间向量，得到n个空间向量，其中，可移动空间的可移动空间点可以包括点P1，目标点可以为机器人的中心点O，其中一个空间向量可以为向量OP1，指定点可以为AB线上的点。
在操作S407，从n个空间向量中筛选与梯门的等效坐标向量相交的目标向量，得到目标向量集，其中，梯门的等效坐标向量可以包括向量G1G4。
在操作S408，针对目标向量集中的每个目标向量，判断目标向量与等效坐标向量之间的相交点至目标可移动空间点的距离是否满足预设距离条件。在目标向量与等效坐标向量之间的相交点至目标可移动空间点的距离满足预设距离条件的情况下，执行操作S409；在目标向量与等效坐标向量之间的相交点至目标可移动空间点的距离不满足预设距离条件的情况下，执行操作S410。
在操作S409，控制机器人通过梯门进入目标电梯。
在操作S410，控制机器人在目标候梯位置继续等待，并执行操作S402。
在操作S411，结束进梯任务。
根据本公开的实施例，点G1、G4、A和B组成的电梯门凹槽区域，机器人在电梯门凹槽区域停止可能会导致卡顿的情况，因此机器人在到达电梯门前AB线时需要判断电梯内部空间是否满足机器人进入的条件。只有当电梯内部空间满足机器人进入条件时，机器人才会继续执行任务，否则取消进电梯任务，以避免由于非必要挤电梯导致任务执行时间过长影响乘梯体验。
根据本公开的实施例，上述激光数据包括激光点的角度数据；上述根据由上述机器人采集的激光数据确定可移动空间包括：根据上述激光点的角度数据确定满足预设角度阈值的激光点，得到目标激光点集，其中，上述预设角度阈值包括根据在上述预设角度阈值内的激光点确定的可移动空间，能够覆盖上述目标电梯的电梯区域；从上述激光数据中提取与上述目标激光点集对应的激光数据，得到目标激光数据；根据上述目标激光数据确定上述目标电梯的上述可移动空间。
根据本公开的实施例，激光点的角度数据例如可以包括在机器人坐标系下，激光点相对于坐标原点的角度。
根据本公开的实施例，预设角度阈值可以包括机器人两侧的角度最大值，确保根据在该预设角度阈值范围内的激光点得到的可移动空间，能够覆盖目标电梯的电梯区域。
根据本公开的实施例，通过从激光数据中提取与目标激光点集对应的激光数据，得到目标激光数据，再根据目标激光数据确定可移动空间，由于仅对能够覆盖电梯内部区域的激光点的激光数据进行处理，减少了数据处理量，有助于降低机器人的处理效率。
根据本公开的实施例，上述目标激光点集包括k个目标激光点，其中，k≥1；其中，上述根据上述目标激光数据确定上述可移动空间包括：在上述机器人的坐标系下，针对上述目标激光点集中的每个目标激光点，确定上述目标激光点所在的方向，得到与上述目标激光点对应的激光方向；确定在上述激光方向上的可移动空间点边界值，得到k个上述可移动空间点边界值；根据k个上述可移动空间点边界值确定上述可移动空间。
图5示意性示出了根据本公开实施例的可移动空间确定方法的流程图。
如图5所示，该实施例的方法包括操作S501～操作S506。
在操作S501，根据激光数据中激光点的角度数据确定满足预设角度阈值的激光点，得到目标激光点集。
在操作S502，从激光数据中提取与目标激光点集对应的激光数据，得到目标激光数据。
在操作S503，在机器人的坐标系下，针对目标激光点集中的第j目标激光点，确定第j目标激光点所在的方向，得到与第j目标激光点对应的第j激光方向。
在操作S504，确定在第j激光方向上的可移动空间点边界值，得到第j可移动空间点边界值。
在操作S505，遍历目标激光点集中的每个目标激光点，得到多个 可移动空间点边界值。
在操作S506，根据上述多个可移动空间点边界值确定可移动空间。
根据本公开的实施例，上述确定在上述激光方向上的可移动空间点边界值包括：操作S1，确定上述激光方向相对于上述机器人的坐标系中基准轴的角度，得到目标角度；操作S2，针对上述目标激光点集中的第i目标激光点，在上述第i目标激光点旋转上述目标角度的情况下，确定与上述第i目标激光点对应的第i横向距离，其中，1≤i≤k；操作S3，在上述第i横向距离小于预设横向距离阈值的情况下，获取上述第i目标激光点的纵坐标值，其中，上述预设横向距离阈值表征上述机器人在横向的障碍物参考范围；操作S4，在上述第i目标激光点的纵坐标值小于当前可行边界阈值的情况下，利用上述第i目标激光点的纵坐标值更新上述当前可行边界阈值，得到更新后的可行边界阈值；操作S5，遍历上述目标激光点集，循环执行操作S2-操作S4以循环更新当前可行边界阈值，直到遍历上述目标激光点集中的目标激光点之后，结束对当前可行边界阈值的更新，得到最终可行边界阈值；操作S6，确定上述最终可行边界阈值为在上述激光方向上的可移动空间点边界值。
图6示意性示出了根据本公开实施例的可移动空间点边界值确定方法的流程图。
如图6所示，针对第j激光方向上的可移动空间点边界值的确定方法包括操作S601～操作S608。
在操作S601，确定第j激光方向相对于机器人的坐标系中基准轴的角度，得到第j目标角度。
在操作S602，按照顺序遍历目标激光点集中的目标激光点，针对目标激光点集中的当前目标激光点，在当前目标激光点旋转第j目标角度的情况下，确定与当前目标激光点对应的当前横向距离。
在操作S603，判断当前横向距离是否小于预设横向距离阈值，其中，预设横向距离阈值表征机器人在横向的障碍物参考范围。在当前横向距离小于预设横向距离阈值的情况下，执行操作S604；在当前横 向距离大于等于预设横向距离阈值的情况下，执行操作S602。
在操作S604，获取当前目标激光点的纵坐标值。
在操作S605，判断当前目标激光点的纵坐标值是否小于当前可行边界阈值。在当前目标激光点的纵坐标值小于当前可行边界阈值的情况下，执行操作S606；在当前目标激光点的纵坐标值大于等于当前可行边界阈值的情况下，执行操作S602。
在操作S606，利用当前目标激光点的纵坐标值更新当前可行边界阈值，得到更新后的可行边界阈值。
在操作S607，循环执行操作S602-操作S606以更新当前可行边界阈值，直到遍历目标激光点集中的目标激光点之后，结束对当前可行边界阈值的更新，得到最终可行边界阈值。
在操作S608，确定最终可行边界阈值为在第j激光方向上的可移动空间点边界值。
根据本公开的实施例，基于激光数据构建可移动空间，具有对定位偏差容忍度高，通向电梯的窄通道场景下通行能力强等优点。
根据本公开的实施例，上述用于机器人的控制方法还包括：确定用于表征目标延长点与上述目标电梯的中心等效点之间空间关系的延长向量，其中，上述目标延长点为上述目标点向纵轴负方向延伸预设长度后的点；在上述延长向量与上述等效坐标向量之间不相交的情况下，确定上述机器人完全通过上述梯门，并进入上述目标电梯内。
根据本公开的实施例，在机器人进入电梯后，机器人的尾部与梯门的空间需要满足乘梯人进出电梯。通过判断目标延长点是否进入电梯来判断机器人的尾部与梯门的空间是否满足乘梯人进出电梯。
图7示意性示出了根据本公开实施例的包含目标延长点的电梯区域示意图。
如图7所示，将机器人尾部向纵轴负方向延伸长度S，得到向量B1B2，此处的长度S根据实际情况确定，以机器人进入电梯后尾部与电梯门的空间至少要满足乘梯人进入电梯为准。机器人尾部的延伸向量B1B2均进入电梯的情况下，表征机器人完成进电梯任务。图7中 的点F为电梯内部的可移动空间点；点Gt为机器人中心点O和向量G2G3的交点；L1、L2分别是点B1、B2到向量G1G4的距离。
图8示意性示出了根据本公开实施例的机器人完全进入电梯确定方法的流程图。
如图7和图8所示，该实施例的机器人完全进入电梯的确定方法包括操作S801～操作S808。
在操作S801，确定向量B1Gt和B2Gt。
在操作S802，判断向量B1Gt、B2Gt与向量G1G4之间是否存在交点。在确定向量B1Gt、B2Gt与向量G1G4之间存在交点的情况下，执行操作S803；在确定向量B1Gt、B2Gt与向量G1G4之间不存在交点的情况下，执行操作S808。
在操作S803，判断交点数量是否为2。在交点数量为2的情况下，执行操作S804～操作S805；在交点数量不是2的情况下，执行操作S806～操作S807。
在操作S804，确定点B1、B2到向量G1G4的距离，得到L1和L2。
在操作S805，确定L1和L2中的最大值为L，以便于利用L值确定前向目标点，并根据前向目标点控制机器人行进。
在操作S806，从向量B1Gt和B2Gt中，确定与向量G1G4相交的向量，得到相交向量。
在操作S807，确定与相交向量对应的点到向量G1G4的距离为L，以便于根据L值确定前向目标点，并根据前向目标点控制机器人行进其中，L为机器人尾部B1B2尚未进入电梯的最大长度。
在操作S808，确定机器人完成进电梯任务。
根据本公开的实施例，上述用于机器人的控制方法还包括：在上述控制上述机器人通过上述梯门进入上述目标电梯之前，根据上述目标向量集，从上述目标可移动空间点中确定前向目标点，其中，上述前向目标点所在的方向为上述机器人的前进方向。
需要说明的是，本公开实施例中的激光数据是定周期获取的，可 移动空间和前向目标点也是定周期确定的。因此，本公开的方法是定周期根据激光数据确定可移动空间，并确定前向目标点。
根据本公开的实施例，上述目标向量集包括m个上述目标向量，m≥2；其中，上述根据上述目标向量集，从上述目标可移动空间点中确定前向目标点包括：针对上述目标向量集中的每个目标向量，确定上述目标向量相对于参考向量的夹角，得到与上述目标向量对应的向量夹角值；根据上述目标延长点到上述等效坐标向量的距离、与上述目标向量对应的向量夹角值和上述机器人的旋转半径确定参考值；在上述目标向量的线段长度满足参考值的情况下，确定与上述目标可移动空间点为备选前向目标点；从备选前向目标点中确定与最小向量夹角值对应的备选前向目标点，得到上述前向目标点。
根据本公开的实施例，根据目标延长点到等效坐标向量的距离、与目标向量对应的向量夹角值和机器人的旋转半径确定参考值的计算公式如下：L/cosα+R，其中，L为目标延长点到等效坐标向量的距离，即机器人尾部B1B2尚未进入电梯的最大长度；α为与目标向量对应的向量夹角值；R为机器人的旋转半径。
图9示意性示出了根据本公开实施例的备选前向目标点的确定方法的流程图。
结合图7和图9所示，该实施例的确定方法包括操作S901～操作907。
在操作S901，针对目标向量集中的每个目标向量，确定目标向量相对于参考向量的夹角，得到与目标向量对应的向量夹角值。
在操作S902，根据目标延长点到等效坐标向量的距离、与目标向量对应的向量夹角值和机器人的旋转半径确定参考值。
在操作S903，判断目标向量的线段长度是否满足参考值。在目标向量的线段长度满足参考值的情况下，执行操作S904；在目标向量的线段长度不满足参考值的情况下，执行操作S905。
在操作S904，确定目标可移动空间点为备选前向目标点，其中，目标可移动空间点与目标向量对应，然后执行操作S906。
在操作S905，确定目标可移动空间点不是备选前向目标点，其中，目标可移动空间点与目标向量对应，然后执行操作S906。
在操作S906，遍历目标向量集中的每个目标向量，循环执行操作S901～操作S905，得到多个备选前向目标点。
在操作S907，从多个备选前向目标点中确定与最小向量夹角值对应的备选前向目标点，得到前向目标点。
根据本公开的实施例，上述目标向量集包括m个上述目标向量，m≥2；其中，上述根据上述目标向量集，从上述目标可移动空间点中确定前向目标点包括：针对上述目标向量集中的每个目标向量，确定上述目标向量相对于参考向量的夹角，得到与上述目标向量对应的夹角绝对值，最终得到m个夹角绝对值，其中，上述参考向量为表征上述目标点与上述目标电梯的中心等效点之间空间关系的向量；根据上述m个夹角绝对值，从上述目标可移动空间点中确定上述前向目标点。
根据本公开的实施例，上述根据上述m个夹角绝对值，从上述目标可移动空间点中确定上述前向目标点包括：从上述m个夹角绝对值中确定数值最小的夹角绝对值，得到目标夹角绝对值；从上述目标可移动空间点中，确定与上述目标夹角绝对值对应的可移动空间点，得到上述前向目标点。
根据本公开的实施例，根据可移动空间和参考目标点灵活选择前向目标点，以提高机器人进电梯的成功率。
根据本公开的实施例，遍历可移动空间点，判断机器人原点和可移动空间点组成的向量和向量G1G4是否相交，并找到相交的可移动空间点中与参考向量的角度绝对值最小的可移动空间点作为前向目标点，以提高机器人进入电梯的顺畅性。
根据本公开的实施例，上述方法还包括：根据前向目标点，控制机器人沿前向目标点方法通过梯门进入目标电梯。
根据本公开的实施例，上述用于机器人的控制方法还包括：在上述前向目标点所在的方向上的可行距离大于等于预设值的情况下，控制上述机器人沿上述前向目标点所在的方向移动，其中，上述预设值 根据上述机器人的速度、上述机器人的加速度和距离补偿值确定。
根据本公开的实施例，预设值s可以采用如下公式计算：v2/2a+s0；其中，v表示机器人的行进速度，a表示加速度，s0为距离补充值，s0可根据实际应用场景和机器人控制精度配置
根据本公开的实施例，在上述前向目标点所在的方向上的可行距离小于预设值的情况下，控制机器人及时减速以防止与障碍物发生碰撞。
根据本公开的实施例，采用常用的路径追踪算法计算机器人的行进速度。
根据本公开的实施例，机器人在进电梯之前首先判断电梯门是否开启，只有当电梯门开启时，机器人才会执行进电梯任务。然后基于机器人采集的激光数据，确定机器人在覆盖电梯空间范围内各方向上所能行驶的最远距离，从而构建可移动空间。在机器人行驶至电梯门前时，针对可移动空间的每个可移动空间点，确定用于表征目标点与可移动空间点之间空间关系的空间向量，得到多个空间向量，之后根据多个空间向量判断可移动空间是否满足机器人进入的条件，只有在可移动空间满足进入条件时机器人才会继续执行进电梯任务，在可移动空间不满足进入条件的情况下，机器人不进入电梯，避免由于机器人非必要的挤电梯导致乘电梯体验差等情况，同时有助于提高机器人进梯成功率。
需要说明的是，本公开实施例中的流程图所示的操作除非明确说明不同操作之间存在执行的先后顺序，或者不同操作在技术实现上存在执行的先后顺序，否则，多个操作之间的执行顺序可以不分先后，多个操作也可以同时执行。
基于上述用于机器人的控制方法，本公开还提供了一种用于机器人的控制装置。以下将结合图10对该装置进行详细描述。
图10示意性示出了根据本公开实施例的用于机器人的控制装置的结构框图。
如图10所示，该实施例的用于机器人的控制装置1000包括第一 控制模块1010、第一确定模块1020、第二确定模块1030和第二控制模块1040。
第一控制模块1010用于控制机器人移动至与目标电梯对应的目标候梯位置。在一实施例中，第一控制模块1010可以用于执行前文描述的操作S210，在此不再赘述。
第一确定模块1020用于在确定上述目标电梯的梯门开启的情况下，根据由上述机器人采集的激光数据确定可移动空间，其中，上述可移动空间由n个可移动空间点围合形成，其中，n≥1。在一实施例中，第一确定模块1020可以用于执行前文描述的操作S220，在此不再赘述。
第二确定模块1030用于针对上述n个可移动空间点中的每个可移动空间点，确定用于表征目标点与上述可移动空间点之间空间关系的空间向量，得到n个上述空间向量，其中，上述目标点位于上述机器人上。在一实施例中，第二确定模块1030可以用于执行前文描述的操作S230，在此不再赘述。
第二控制模块1040用于根据n个上述空间向量控制上述机器人的移动状态。在一实施例中，第二控制模块1040可以用于执行前文描述的操作S240，在此不再赘述。
根据本公开的实施例，上述第二控制模块包括：筛选子模块和控制子模块。
筛选子模块，用于在上述机器人移动至指定点的情况下，从n个上述空间向量中筛选与上述梯门的等效坐标向量相交的目标向量，得到目标向量集，其中，上述等效坐标向量用于表征上述梯门上的等效点之间空间关系的坐标向量，上述指定点位于上述目标电梯外部，且靠近上述目标电梯的梯门凹槽。
控制子模块，用于在上述目标向量和上述等效坐标向量之间的相交点至目标可移动空间点的距离满足预设距离条件的情况下，控制上述机器人通过上述梯门进入上述目标电梯，其中，上述目标可移动空间点与上述目标向量对应。
根据本公开的实施例，上述激光数据包括激光点的角度数据。
根据本公开的实施例，上述第一确定模块包括：第一确定子模块、提取子模块和第二确定子模块。
第一确定子模块，用于根据上述激光点的角度数据确定满足预设角度阈值的激光点，得到目标激光点集，其中，上述预设角度阈值包括根据在上述预设角度阈值内的激光点确定的可移动空间，能够覆盖上述目标电梯的电梯区域。
提取模块，用于从上述激光数据中提取与上述目标激光点集对应的激光数据，得到目标激光数据。
第二确定子模块，用于根据上述目标激光数据确定上述可移动空间。
根据本公开的实施例，上述目标激光点集包括k个目标激光点，其中，k≥1。
根据本公开的实施例，上述第二确定子模块包括：第一确定单元、第二确定单元和第三确定单元。
第一确定单元，用于在上述机器人的坐标系下，针对上述目标激光点集中的每个目标激光点，确定上述目标激光点所在的方向，得到与上述目标激光点对应的激光方向。
第二确定单元，用于确定在上述激光方向上的可移动空间点边界值，得到k个上述可移动空间点边界值。
第三确定单元，用于根据k个上述可移动空间点边界值确定上述可移动空间。
根据本公开的实施例，上述第二确定单元包括：第一确定子单元、第二确定子单元、获取子单元、更新子单元、遍历子单元和第三确定子单元。
第一确定子单元，用于确定上述激光方向相对于上述机器人的坐标系中基准轴的角度，得到目标角度。
第二确定子单元，用于针对上述目标激光点集中的第i目标激光点，在上述第i目标激光点旋转上述目标角度的情况下，确定与上述 第i目标激光点对应的第i横向距离，其中，1≤i≤k。
获取子单元，用于在上述第i横向距离小于预设横向距离阈值的情况下，获取上述第i目标激光点的纵坐标值，其中，上述预设横向距离阈值表征上述机器人在横向的障碍物参考范围。
更新子单元，用于在上述第i目标激光点的纵坐标值小于当前可行边界阈值的情况下，利用上述第i目标激光点的纵坐标值更新上述当前可行边界阈值，得到更新后的可行边界阈值。
遍历子单元，用于遍历上述目标激光点集，循环执行第二确定子单元、获取子单元和更新子单元作执行的操作，以循环更新当前可行边界阈值，直到遍历上述目标激光点集中的目标激光点之后，结束对当前可行边界阈值的更新，得到最终可行边界阈值。
第三确定子单元，用于确定上述最终可行边界阈值为在上述激光方向上的可移动空间点边界值。
根据本公开的实施例，上述用于机器人的控制装置还包括：第三确定模块和第四确定模块。
第三确定模块，用于确定用于表征目标延长点与上述目标电梯的中心等效点之间空间关系的延长向量，其中，上述目标延长点为上述目标点向纵轴负方向延伸预设长度后的点。
第四确定模块，用于在上述延长向量与上述等效坐标向量之间不相交的情况下，确定上述机器人完全通过上述梯门，并进入上述目标电梯内。
根据本公开的实施例，上述用于机器人的控制装置还包括第五确定模块。
第五确定模块，用于在上述控制上述机器人通过上述梯门进入上述目标电梯之前，根据上述目标向量集，从上述目标可移动空间点中确定前向目标点，其中，上述前向目标点所在的方向为上述机器人的前进方向。
根据本公开的实施例，上述目标向量集包括m个上述目标向量，m≥2。
根据本公开的实施例，其中，上述第五确定模块包括：第三确定子模块和第四确定子模块。
第三确定子模块，用于针对上述目标向量集中的每个目标向量，确定上述目标向量相对于参考向量的夹角，得到与上述目标向量对应的夹角绝对值，最终得到m个夹角绝对值，其中，上述参考向量为表征上述目标点与上述目标电梯的中心等效点之间空间关系的向量。
第四确定子模块，用于根据上述m个夹角绝对值，从上述目标可移动空间点中确定上述前向目标点。
根据本公开的实施例，上述第四确定子模块包括：第四确定单元和第五确定单元。
第四确定单元，用于从上述m个夹角绝对值中确定数值最小的夹角绝对值，得到目标夹角绝对值。
第五确定单元，用于从上述目标可移动空间点中，确定与上述目标夹角绝对值对应的可移动空间点，得到上述前向目标点。
根据本公开的实施例，上述目标向量集包括m个上述目标向量，m≥2
根据本公开的实施例，上述第五确定模块包括：上述第五确定子模块、第六确定子模块、第七确定子模块和第八确定子模块。
第五确定子模块，用于针对上述目标向量集中的每个目标向量，确定上述目标向量相对于参考向量的夹角，得到与上述目标向量对应的向量夹角值。
第六确定子模块，用于根据上述目标延长点到上述等效坐标向量的距离、与上述目标向量对应的向量夹角值和上述机器人的旋转半径确定参考值。
第七确定子模块，用于在上述目标向量的线段长度满足参考值的情况下，确定与上述目标可移动空间点为备选前向目标点。
第八确定子模块，用于从备选前向目标点中确定与最小向量夹角值对应的备选前向目标点，得到上述前向目标点。
根据本公开的实施例，上述控制子模块还用于在上述前向目标点 所在的方向上的可行距离大于等于预设值的情况下，控制上述机器人沿上述前向目标点所在的方向移动，其中，上述预设值根据上述机器人的速度、上述机器人的加速度和距离补偿值确定。
需要说明的是，本公开装置部分的实施例与本公开方法部分的实施例对应相同或类似，本公开在此不再赘述。
根据本公开的实施例的模块、子模块、单元、子单元中的任意多个、或其中任意多个的至少部分功能可以在一个模块中实现。根据本公开实施例的模块、子模块、单元、子单元中的任意一个或多个可以被拆分成多个模块来实现。根据本公开实施例的模块、子模块、单元、子单元中的任意一个或多个可以至少被部分地实现为硬件电路，例如现场可编程门阵列(FPGA)、可编程逻辑阵列(PLA)、片上系统、基板上的系统、封装上的系统、专用集成电路(ASIC)，或可以通过对电路进行集成或封装的任何其他的合理方式的硬件或固件来实现，或以软件、硬件以及固件三种实现方式中任意一种或以其中任意几种的适当组合来实现。或者，根据本公开实施例的模块、子模块、单元、子单元中的一个或多个可以至少被部分地实现为计算机程序模块，当该计算机程序模块被运行时，可以执行相应的功能。
例如，第一控制模块1010、第一确定模块1020、第二确定模块1030和第二控制模块1040中的任意多个可以合并在一个模块/单元/子单元中实现，或者其中的任意一个模块/单元/子单元可以被拆分成多个模块/单元/子单元。或者，这些模块/单元/子单元中的一个或多个模块/单元/子单元的至少部分功能可以与其他模块/单元/子单元的至少部分功能相结合，并在一个模块/单元/子单元中实现。根据本公开的实施例，第一控制模块1010、第一确定模块1020、第二确定模块1030和第二控制模块1040中的至少一个可以至少被部分地实现为硬件电路，例如现场可编程门阵列(FPGA)、可编程逻辑阵列(PLA)、片上系统、基板上的系统、封装上的系统、专用集成电路(ASIC)，或可以通过对电路进行集成或封装的任何其他的合理方式等硬件或固件来实现，或以软件、硬件以及固件三种实现方式中任意一种或以其中任意几种的适当组合来实现。或 者，第一控制模块1010、第一确定模块1020、第二确定模块1030和第二控制模块1040中的至少一个可以至少被部分地实现为计算机程序模块，当该计算机程序模块被运行时，可以执行相应的功能。
图11示意性示出了根据本公开实施例的适于实现上文描述的方法的电子设备的框图。图11示出的电子设备仅仅是一个示例，不应对本公开实施例的功能和使用范围带来任何限制。
如图11所示，根据本公开实施例的电子设备1100包括处理器1101，其可以根据存储在只读存储器(ROM)1102中的程序或者从存储部分1108加载到随机访问存储器(RAM)1103中的程序而执行各种适当的动作和处理。处理器1101例如可以包括通用微处理器(例如CPU)、指令集处理器和/或相关芯片组和/或专用微处理器(例如，专用集成电路(ASIC))，等等。处理器1101还可以包括用于缓存用途的板载存储器。处理器1101可以包括用于执行根据本公开实施例的方法流程的不同动作的单一处理单元或者是多个处理单元。
在RAM 1103中，存储有电子设备1100操作所需的各种程序和数据。处理器1101、ROM 1102以及RAM 1103通过总线1104彼此相连。处理器1101通过执行ROM 1102和/或RAM 1103中的程序来执行根据本公开实施例的方法流程的各种操作。需要注意，所述程序也可以存储在除ROM 1102和RAM 1103以外的一个或多个存储器中。处理器1101也可以通过执行存储在所述一个或多个存储器中的程序来执行根据本公开实施例的方法流程的各种操作。
根据本公开的实施例，电子设备1100还可以包括输入/输出(I/O)接口1105，输入/输出(I/O)接口1105也连接至总线1104。系统1100还可以包括连接至I/O接口1105的以下部件中的一项或多项：包括键盘、鼠标等的输入部分1106；包括诸如阴极射线管(CRT)、液晶显示器(LCD)等以及扬声器等的输出部分1107；包括硬盘等的存储部分1108；以及包括诸如LAN卡、调制解调器等的网络接口卡的通信部分1109。通信部分1109经由诸如因特网的网络执行通信处理。驱动器1110也根据需要连接至I/O接口1105。可拆卸介质1111，诸如磁盘、光盘、磁光盘、 半导体存储器等等，根据需要安装在驱动器1110上，以便于从其上读出的计算机程序根据需要被安装入存储部分1108。
根据本公开的实施例，根据本公开实施例的方法流程可以被实现为计算机软件程序。例如，本公开的实施例包括一种计算机程序产品，其包括承载在计算机可读存储介质上的计算机程序，该计算机程序包含用于执行流程图所示的方法的程序代码。在这样的实施例中，该计算机程序可以通过通信部分1109从网络上被下载和安装，和/或从可拆卸介质1111被安装。在该计算机程序被处理器1101执行时，执行本公开实施例的系统中限定的上述功能。根据本公开的实施例，上文描述的系统、设备、装置、模块、单元等可以通过计算机程序模块来实现。
本公开还提供了一种计算机可读存储介质，该计算机可读存储介质可以是上述实施例中描述的设备/装置/系统中所包含的；也可以是单独存在，而未装配入该设备/装置/系统中。上述计算机可读存储介质承载有一个或者多个程序，当上述一个或者多个程序被执行时，实现根据本公开实施例的方法。
根据本公开的实施例，计算机可读存储介质可以是非易失性的计算机可读存储介质。例如可以包括但不限于：便携式计算机磁盘、硬盘、随机访问存储器(RAM)、只读存储器(ROM)、可擦式可编程只读存储器(EPROM或闪存)、便携式紧凑磁盘只读存储器(CD-ROM)、光存储器件、磁存储器件、或者上述的任意合适的组合。在本公开中，计算机可读存储介质可以是任何包含或存储程序的有形介质，该程序可以被指令执行系统、装置或者器件使用或者与其结合使用。
例如，根据本公开的实施例，计算机可读存储介质可以包括上文描述的ROM 1102和/或RAM 1103和/或ROM 1102和RAM 1103以外的一个或多个存储器。
附图中的流程图和框图，图示了按照本公开各种实施例的系统、方法和计算机程序产品的可能实现的体系架构、功能和操作。在这点上，流程图或框图中的每个方框可以代表一个模块、程序段、或代码的一部分，上述模块、程序段、或代码的一部分包含一个或多个用于实现规定 的逻辑功能的可执行指令。也应当注意，在有些作为替换的实现中，方框中所标注的功能也可以以不同于附图中所标注的顺序发生。例如，两个接连地表示的方框实际上可以基本并行地执行，它们有时也可以按相反的顺序执行，这依所涉及的功能而定。也要注意的是，框图或流程图中的每个方框、以及框图或流程图中的方框的组合，可以用执行规定的功能或操作的专用的基于硬件的系统来实现，或者可以用专用硬件与计算机指令的组合来实现。
本领域技术人员可以理解，本公开的各个实施例和/或权利要求中记载的特征可以进行多种组合和/或结合，即使这样的组合或结合没有明确记载于本公开中。特别地，在不脱离本公开精神和教导的情况下，本公开的各个实施例和/或权利要求中记载的特征可以进行多种组合和/或结合。所有这些组合和/或结合均落入本公开的范围。
以上对本公开的实施例进行了描述。但是，这些实施例仅仅是为了说明的目的，而并非为了限制本公开的范围。尽管在以上分别描述了各实施例，但是这并不意味着各个实施例中的措施不能有利地结合使用。本公开的范围由所附权利要求及其等同物限定。不脱离本公开的范围，本领域技术人员可以做出多种替代和修改，这些替代和修改都应落在本公开的范围之内。

Claims (15)

  1. 一种用于机器人的控制方法，包括：
    控制机器人移动至与目标电梯对应的目标候梯位置；
    在确定所述目标电梯的梯门开启的情况下，根据由所述机器人采集的激光数据确定可移动空间，其中，所述可移动空间由n个可移动空间点围合形成，其中，n≥1；
    针对所述n个可移动空间点中的每个可移动空间点，确定用于表征目标点与所述可移动空间点之间空间关系的空间向量，得到n个所述空间向量，其中，所述目标点位于所述机器人上；以及
    根据n个所述空间向量控制所述机器人的移动状态。
  2. 根据权利要求1所述的方法，其中，所述根据n个所述空间向量控制所述机器人的移动状态包括：
    在所述机器人移动至指定点的情况下，从n个所述空间向量中筛选与所述梯门的等效坐标向量相交的目标向量，得到目标向量集，其中，所述等效坐标向量用于表征所述梯门上的等效点之间空间关系的坐标向量，所述指定点位于所述目标电梯的外部，且靠近所述目标电梯的梯门凹槽；
    在所述目标向量和所述等效坐标向量之间的相交点至目标可移动空间点的距离满足预设距离条件的情况下，控制所述机器人通过所述梯门进入所述目标电梯，其中，所述目标可移动空间点与所述目标向量对应。
  3. 根据权利要求1所述的方法，其中，所述激光数据包括激光点的角度数据；
    所述根据由所述机器人采集的激光数据确定可移动空间包括：
    根据所述激光点的角度数据确定满足预设角度阈值的激光点，得到目标激光点集，其中，所述预设角度阈值包括根据在所述预设角度阈值内的激光点确定的可移动空间，能够覆盖所述目标电梯的电梯区域；
    从所述激光数据中提取与所述目标激光点集对应的激光数据，得到目标激光数据；
    根据所述目标激光数据确定所述可移动空间。
  4. 根据权利要求3所述的方法，其中，所述目标激光点集包括k个目标激光点，其中，k≥1；
    其中，所述根据所述目标激光数据确定所述可移动空间包括：
    在所述机器人的坐标系下，针对所述目标激光点集中的每个目标激光点，确定所述目标激光点所在的方向，得到与所述目标激光点对应的激光方向；
    确定在所述激光方向上的可移动空间点边界值，得到k个所述可移动空间点边界值；
    根据k个所述可移动空间点边界值确定所述可移动空间。
  5. 根据权利要求4所述的方法，其中，所述确定在所述激光方向上的可移动空间点边界值包括：
    操作S1，确定所述激光方向相对于所述机器人的坐标系中基准轴的角度，得到目标角度；
    操作S2，针对所述目标激光点集中的第i目标激光点，在所述第i目标激光点旋转所述目标角度的情况下，确定与所述第i目标激光点对应的第i横向距离，其中，1≤i≤k；
    操作S3，在所述第i横向距离小于预设横向距离阈值的情况下，获取所述第i目标激光点的纵坐标值，其中，所述预设横向距离阈值表征所述机器人在横向的障碍物参考范围；
    操作S4，在所述第i目标激光点的纵坐标值小于当前可行边界阈值的情况下，利用所述第i目标激光点的纵坐标值更新所述当前可行边界阈值，得到更新后的可行边界阈值；
    操作S5，遍历所述目标激光点集，循环执行操作S2-操作S4以循环更新当前可行边界阈值，直到遍历所述目标激光点集中的目标激光点之后，结束对当前可行边界阈值的更新，得到最终可行边界阈值；
    操作S6，确定所述最终可行边界阈值为在所述激光方向上的可移 动空间点边界值。
  6. 根据权利要求2所述的方法，还包括：
    确定用于表征目标延长点与所述目标电梯的中心等效点之间空间关系的延长向量，其中，所述目标延长点为所述目标点向纵轴负方向延伸预设长度后的点；
    在所述延长向量与所述等效坐标向量之间不相交的情况下，确定所述机器人完全通过所述梯门，并进入所述目标电梯内。
  7. 根据权利要求6所述的方法，还包括：
    在所述控制所述机器人通过所述梯门进入所述目标电梯之前，根据所述目标向量集，从所述目标可移动空间点中确定前向目标点，其中，所述前向目标点所在的方向为所述机器人的前进方向。
  8. 根据权利要求7所述的方法，其中，所述目标向量集包括m个所述目标向量，m≥1；
    其中，所述根据所述目标向量集，从所述目标可移动空间点中确定前向目标点包括：
    针对所述目标向量集中的每个目标向量，确定所述目标向量相对于参考向量的夹角，得到与所述目标向量对应的夹角绝对值，最终得到m个夹角绝对值，其中，所述参考向量为表征所述目标点与所述目标电梯的中心等效点之间空间关系的向量；
    根据所述m个夹角绝对值，从所述目标可移动空间点中确定所述前向目标点。
  9. 根据权利要求8所述的方法，其中，所述根据所述m个夹角绝对值，从所述目标可移动空间点中确定所述前向目标点包括：
    从所述m个夹角绝对值中确定数值最小的夹角绝对值，得到目标夹角绝对值；
    从所述目标可移动空间点中，确定与所述目标夹角绝对值对应的可移动空间点，得到所述前向目标点。
  10. 根据权利要求7所述的方法，其中，所述目标向量集包括m个所述目标向量，m≥1；
    其中，所述根据所述目标向量集，从所述目标可移动空间点中确定前向目标点包括：
    针对所述目标向量集中的每个目标向量，确定所述目标向量相对于参考向量的夹角，得到与所述目标向量对应的向量夹角值；
    根据所述目标延长点到所述等效坐标向量的距离、与所述目标向量对应的向量夹角值和所述机器人的旋转半径确定参考值；
    在所述目标向量的线段长度满足参考值的情况下，确定与所述目标可移动空间点为备选前向目标点；
    从备选前向目标点中确定与最小向量夹角值对应的备选前向目标点，得到所述前向目标点。
  11. 根据权利要求7所述的方法，还包括：
    在所述前向目标点所在的方向上的可行距离大于等于预设值的情况下，控制所述机器人沿所述前向目标点所在的方向移动，其中，所述预设值根据所述机器人的速度、所述机器人的加速度和距离补偿值确定。
  12. 一种用于机器人的控制装置，包括：
    第一控制模块，用于控制机器人移动至与目标电梯对应的目标候梯位置；
    第一确定模块，用于在确定所述目标电梯的梯门开启的情况下，根据由所述机器人采集的激光数据确定可移动空间，其中，所述可移动空间由n个可移动空间点围合形成，其中，n≥1；
    第二确定模块，用于针对所述n个可移动空间点中的每个可移动空间点，确定用于表征目标点与所述可移动空间点之间空间关系的空间向量，得到n个所述空间向量，其中，所述目标点位于所述机器人上；以及
    第二控制模块，用于根据n个所述空间向量控制所述机器人的移动状态。
  13. 一种电子设备，包括：
    一个或多个处理器；
    存储器，用于存储一个或多个程序，
    其中，当所述一个或多个程序被所述一个或多个处理器执行时，使得所述一个或多个处理器实现权利要求1～11中任一项所述的方法。
  14. 一种计算机可读存储介质，其上存储有可执行指令，该指令被处理器执行时使处理器实现权利要求1～11中任一项所述的方法。
  15. 一种计算机程序产品，包括计算机程序，所述计算机程序被处理器执行时实现根据权利要求1～11中任一项所述的方法。
PCT/CN2023/089464 2022-08-03 2023-04-20 用于机器人的控制方法、装置、电子设备及存储介质 WO2024027210A1 (zh)

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
CN202210929618.0A CN115167454A (zh) 2022-08-03 2022-08-03 用于机器人的控制方法、装置、电子设备及存储介质
CN202210929618.0 2022-08-03

Publications (1)

Publication Number Publication Date
WO2024027210A1 true WO2024027210A1 (zh) 2024-02-08

Family

ID=83477868

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/CN2023/089464 WO2024027210A1 (zh) 2022-08-03 2023-04-20 用于机器人的控制方法、装置、电子设备及存储介质

Country Status (2)

Country Link
CN (1) CN115167454A (zh)
WO (1) WO2024027210A1 (zh)

Families Citing this family (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN115167454A (zh) * 2022-08-03 2022-10-11 北京京东乾石科技有限公司 用于机器人的控制方法、装置、电子设备及存储介质

Citations (11)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JP2011088721A (ja) * 2009-10-23 2011-05-06 Fuji Heavy Ind Ltd 自律走行ロボット及び自律走行ロボットの制御システム
JP2013131100A (ja) * 2011-12-22 2013-07-04 Univ Of Electro-Communications 人数予測方法、人数予測装置、移動ロボット及びプログラム
CN106965198A (zh) * 2017-03-30 2017-07-21 上海木爷机器人技术有限公司 机器人控制方法和装置
CN110488313A (zh) * 2019-08-30 2019-11-22 上海有个机器人有限公司 一种移动机器人识别电梯内拥挤度的方法
CN110713087A (zh) * 2019-10-21 2020-01-21 北京猎户星空科技有限公司 一种电梯门状态检测方法及装置
CN111728533A (zh) * 2020-06-01 2020-10-02 珠海市一微半导体有限公司 一种机器人进出电梯的移动控制方法、激光机器人及芯片
CN112130574A (zh) * 2020-09-30 2020-12-25 拉扎斯网络科技（上海）有限公司 机器人的控制方法、装置、电子设备及计算机存储介质
US20210339399A1 (en) * 2020-04-29 2021-11-04 Cobalt Robotics Inc. Mobile robot for elevator interactions
CN114200472A (zh) * 2021-11-12 2022-03-18 广东盈峰智能环卫科技有限公司 一种可通行区域的实时检测方法、装置、终端及存储介质
KR20220102379A (ko) * 2021-01-13 2022-07-20 주식회사 트위니 다중 로봇의 엘리베이터 승하차 방법 및 장치
CN115167454A (zh) * 2022-08-03 2022-10-11 北京京东乾石科技有限公司 用于机器人的控制方法、装置、电子设备及存储介质

Patent Citations (11)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JP2011088721A (ja) * 2009-10-23 2011-05-06 Fuji Heavy Ind Ltd 自律走行ロボット及び自律走行ロボットの制御システム
JP2013131100A (ja) * 2011-12-22 2013-07-04 Univ Of Electro-Communications 人数予測方法、人数予測装置、移動ロボット及びプログラム
CN106965198A (zh) * 2017-03-30 2017-07-21 上海木爷机器人技术有限公司 机器人控制方法和装置
CN110488313A (zh) * 2019-08-30 2019-11-22 上海有个机器人有限公司 一种移动机器人识别电梯内拥挤度的方法
CN110713087A (zh) * 2019-10-21 2020-01-21 北京猎户星空科技有限公司 一种电梯门状态检测方法及装置
US20210339399A1 (en) * 2020-04-29 2021-11-04 Cobalt Robotics Inc. Mobile robot for elevator interactions
CN111728533A (zh) * 2020-06-01 2020-10-02 珠海市一微半导体有限公司 一种机器人进出电梯的移动控制方法、激光机器人及芯片
CN112130574A (zh) * 2020-09-30 2020-12-25 拉扎斯网络科技（上海）有限公司 机器人的控制方法、装置、电子设备及计算机存储介质
KR20220102379A (ko) * 2021-01-13 2022-07-20 주식회사 트위니 다중 로봇의 엘리베이터 승하차 방법 및 장치
CN114200472A (zh) * 2021-11-12 2022-03-18 广东盈峰智能环卫科技有限公司 一种可通行区域的实时检测方法、装置、终端及存储介质
CN115167454A (zh) * 2022-08-03 2022-10-11 北京京东乾石科技有限公司 用于机器人的控制方法、装置、电子设备及存储介质

Also Published As

Publication number Publication date
CN115167454A (zh) 2022-10-11

Similar Documents

Publication Publication Date Title
US10678248B2 (en) Fast trajectory planning via maneuver pattern selection
US11332132B2 (en) Method of handling occlusions at intersections in operation of autonomous vehicle
Li et al. Real-time trajectory planning for autonomous urban driving: Framework, algorithms, and verifications
JP2022553310A (ja) 衝突ゾーンに基づく軌道修正
US20220410939A1 (en) Collision detection method, electronic device, and medium
WO2021142799A1 (zh) 路径选择方法和路径选择装置
US20230358554A1 (en) Routing graph management in autonomous vehicle routing
CN110834631A (zh) 一种行人避让方法、装置、车辆及存储介质
WO2021169993A1 (zh) 自动驾驶地图的构建方法及相关装置
WO2022104774A1 (zh) 目标检测方法和装置
US10049578B2 (en) Travel command generation device
WO2022056770A1 (zh) 一种路径规划方法和路径规划装置
CN113009918B (zh) 路径规划方法、装置、系统及可读存储介质
WO2024027210A1 (zh) 用于机器人的控制方法、装置、电子设备及存储介质
WO2021017504A1 (zh) 运动轨迹预测方法和装置
JP2019021202A (ja) 移動ロボットの制御装置と制御方法
GB2609803A (en) System and method for intersection management by an autonomous vehicle
WO2022052856A1 (zh) 基于交通工具的数据处理方法、装置、计算机及存储介质
US20230001953A1 (en) Planning-aware prediction for control-aware autonomous driving modules
US20220155082A1 (en) Route comparison for vehicle routing
US11293767B2 (en) Dynamic drop off and pick up of passengers via autonomous vehicles
US20210398014A1 (en) Reinforcement learning based control of imitative policies for autonomous driving
WO2021027966A1 (zh) 行进方法、可行进设备和存储介质
US20220396290A1 (en) Apparatus for Controlling Vehicle, System Including Same and Method Thereof
US20210095977A1 (en) Revising self-driving vehicle routes in response to obstructions